{"as_of":"2026-08-04T03:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1e9df7ea22987096eec72c23916a62d5f7dbfb4a9bd279e3257da6f2e22b9e52","coverage":[{"denominator":132,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T16:10:51.471822Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.10091/citation-record","integrity":"/paper/2606.10091/integrity","json":"/paper/2606.10091/citation-record.json","paper":"/paper/2606.10091"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"On the alignment of group fairness with attribute privacy","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:ab855dbe331e5ad5dcb6daa8fe2b7edf2122bb9146c4cca56a92e3563de7f617","observation_id":"f09afa7e-b046-40ec-8094-9d2b2649b2f3","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01740","last_updated":"2023-04-21T09:01:24Z","snapshot_observed_at":"2026-08-02T09:43:06.335352Z","submitted_at":"2023-02-03T14:00:05Z","title":"SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification","version":2},"cited_work":{"arxiv_id":"2302.01740","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.01740","snapshot_observed_at":"2026-07-03T02:07:33.537996Z","title":"Sok: A systematic evaluation of backdoor trigger characteristics in image classification","venue":null,"work_id":"c6658d37-4607-440f-b83c-5cc740f180a7","year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2302.01740","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:afc9312f59838b7f6422b9a51cde2bacdb808f392af977a0643961d3a563ce76","observation_id":"c0db3a41-5f72-49b5-8eee-313eaa77802b","resolution":{"observed_at":"2026-07-03T02:07:33.539735Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.10242","last_updated":"2024-11-15T14:55:01Z","snapshot_observed_at":"2026-07-06T19:50:56.818819Z","submitted_at":"2024-11-15T14:55:01Z","title":"Measuring Non-Adversarial Reproduction of Training Data in Large Language Models","version":1},"cited_work":{"arxiv_id":"2411.10242","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.10242","snapshot_observed_at":"2026-07-03T02:07:33.490588Z","title":"Measuring non-adversarial repro- duction of training data in large language models","venue":null,"work_id":"0c6b7885-cc2e-46ec-b86f-a49f7aa43027","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2411.10242","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d4436a4a2bf0d6d38f6f78bfe005d79428de09c4cdbcf08f46b46b9f5e9d9fc8","observation_id":"403014c9-b9b9-47b7-a38c-6620ed20f3eb","resolution":{"observed_at":"2026-07-03T02:07:33.492459Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Square attack: a query-efficient black-box adversarial attack via ran- dom search","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:bca6f4c3e7213cb7e1152bc0f895a57345be24cc0e7051fa7f9a3c3a1d00c454","observation_id":"f78a0653-0662-4bf7-bf13-8a93dabf9239","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Static vs","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:e56a3677e3f7cb70499744109390df9ca88b2584fb410cac1f5ee6560e2c2998","observation_id":"ff37f54e-8506-4a26-a206-d48799ef54e4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Blind backdoors in deep learning models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c219986dad03c0a441ae6e344e0b1b52428150fc3847d417956f49f8cb328b97","observation_id":"9107eeff-f4a9-4aa4-89d0-95277d2d0a4c","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"CSI NN: Reverse engineering of neu- ral network architectures through electromagnetic side channel","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:4af24fb64d5c324bd451825b51d311b0d816037049fb840b3ce5497da87f2002","observation_id":"838d4fd6-6acb-44cc-bc4d-2fa5c545b9bd","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Chosen ciphertext attacks against protocols based on the rsa encryption standard pkcs #1","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:e1d9f27b8ad3b811c7590faa18c0ba9beb158e7a71e4b5ba09a138cfef41bded","observation_id":"ddf274b8-a1ea-460c-9e38-31996f25a46a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Sok: Gradient inversion attacks in federated learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:1fe4f2666910b43434ad711417317cbddc943a74a8679c161dfd9d0640f7b518","observation_id":"60c05df6-4978-4eeb-aa5c-e4e543de26b9","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:5c1fde57becf465cc60596bca9e14c09090e9d3d59398bffc773d648b3671c83","observation_id":"739b77c6-4cf8-43c6-9f45-2b1566c40ee4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Membership inference attacks from first principles","venue":null,"work_id":null,"year":1914},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:494e1431c1fb72986f6e8dd6e9b6796e63fb685f7213345f0b06709bfb2f7f9f","observation_id":"c65b88c3-ad14-48cf-af78-c7590a69981c","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"The privacy onion effect: Mem- orization is relative","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:2f24d630da26bdd789e8f6a863ee61805bf1f13f41518392a9bfc6f871b43f34","observation_id":"bb68bef1-7ad3-4117-b141-9b71abc8b8e2","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Extracting training data from diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:6f5817778ea1364fd8936cb9da7f9de1cb95dd8c72f96f779fdc99e08ce438e1","observation_id":"8fd7fcf6-19c0-4ee9-be60-82a01a2550f0","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.06634","last_updated":"2024-07-09T17:44:00Z","snapshot_observed_at":"2026-07-06T17:42:33.242895Z","submitted_at":"2024-03-11T11:46:12Z","title":"Stealing Part of a Production Language Model","version":2},"cited_work":{"arxiv_id":"2403.06634","doi":"10.48550/arxiv.2403.06634","metadata_source":"arxiv_reference","pith_arxiv_id":"2403.06634","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Stealing part of a production language model.arXiv preprint arXiv:2403.06634","venue":null,"work_id":"0ab070c2-82e2-41d8-8d46-379236a08dbe","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2403.06634","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:6f8a98e5d6c15a1f0ba78dda5b01118e7d62454eee89914892f31b166c7e82f9","observation_id":"94efd86d-ba91-4802-af11-79be1c394e34","resolution":{"observed_at":"2026-07-03T02:07:33.530859Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Property inference from poisoning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:aea77b78a86a50926d9cce3deb047fefd1fa94128df623fad5678b970cf543f5","observation_id":"37e2700e-8509-45b7-9198-f2d6abdd943f","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Snap: Efficient extraction of private properties with poisoning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:b6caad5fc460e4f1ddc96499b7199d701d5be95d7a23021086f8fcfb5827a74b","observation_id":"7503234e-c98e-42aa-a60b-7f6f5d7881cf","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.10909","last_updated":"2021-12-26T14:55:54Z","snapshot_observed_at":"2026-07-06T11:11:58.263934Z","submitted_at":"2021-05-23T10:38:23Z","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","version":2},"cited_work":{"arxiv_id":"2105.10909","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2105.10909","snapshot_observed_at":"2026-07-03T02:07:33.503275Z","title":"Killing one bird with two stones: model extraction and attribute inference attacks against bert-based apis","venue":null,"work_id":"efb88f35-96e2-4485-b3c4-97a11d332eae","year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2105.10909","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:13416278c7a07ad69fe3be1ffe69610869b10025178a2b38627938f1874c3bc2","observation_id":"1a9832ca-fc34-45f7-b230-2a474b399ed4","resolution":{"observed_at":"2026-07-03T02:07:33.504781Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Privacy and fairness in federated learning: On the perspective of tradeoff.ACM Comput","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d15d0e6025798570813cadc458c559ee9b9d83fe10c271f2d20e0dd890414f60","observation_id":"9b49b6b0-3ae8-4d06-beef-aaf45630adb4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Amplifying membership exposure via data poisoning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d9039bef55eecd1b77bf5b0022a0864680ad46d0917b8e24c54699e5065584d8","observation_id":"c3d6806d-519a-4925-8167-6e3741168953","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"A method to fa- cilitate membership inference attacks in deep learning models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:3910d085128cafedf3c9f44d9400985ba9a0eefc127bce91d3c9ed0e02ece38f","observation_id":"04cbff13-ee89-4eb0-805f-4a713e495b0d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Long-tailed adversarial training with self-distillation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:bd439598c596026e05492ac6d26b85330eb077daaf3394cc93e062966cd2c8e2","observation_id":"d2175e52-7763-4aac-9063-52ad8657715d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Choquette-Choo et al","venue":null,"work_id":null,"year":1964},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:87f6c6f405f773719e83f1e51ecfb451a93a82a1c1a320397561051ff06ed18e","observation_id":"d18c4694-cca8-40d2-bc5c-4e1c0f901011","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Wild patterns reloaded: A survey of machine learning security against training data poisoning.ACM Comput","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:2a5f8175b204091160b4124622de2ab90e21557f22b69744975f6786ba2619e7","observation_id":"cf5c5184-92d6-4fb1-bb3a-9e067e65af65","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Energy-latency at- tacks via sponge poisoning.Information Sciences, 702:121905, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c82fe51751d2d43a95c4401b416cb0c8c936ea2b00cce3655aa87d1704cc4f8a","observation_id":"acef0602-157c-4dba-9bff-e36f72770b2a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Why do adversarial attacks transfer? explaining transferability of evasion and poi- soning attacks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c3c32b8fcf8f9b12a3bc9c620962a10974b6afc48bf5af4daac03b2cfc0c8a29","observation_id":"e298ed31-75ff-415e-8fa0-6402366228ff","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Vertexserum: Poisoning graph neural networks for link inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:02248b982f53e1914ea79840a1d97512834b36aa08eb75915335d28576128aa0","observation_id":"6c855dc1-de8a-4306-8403-e2404462d165","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Are diffusion models vulnerable to membership inference attacks? InICML, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:18f06af3913187368e00120c292d8dde8d71cc8f4751165578f28d85650a458d","observation_id":"46700f41-feb6-4aa0-be20-7e4adcc130a8","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07841","last_updated":"2024-09-16T13:18:23Z","snapshot_observed_at":"2026-07-06T17:29:00.943463Z","submitted_at":"2024-02-12T17:52:05Z","title":"Do Membership Inference Attacks Work on Large Language Models?","version":2},"cited_work":{"arxiv_id":"2402.07841","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.07841","snapshot_observed_at":"2026-07-04T10:59:46.006014Z","title":"arXiv preprint arXiv:2402.07841 , year=","venue":null,"work_id":"ed6b0b8c-85ff-481a-bf05-90b8c3feab4e","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2402.07841","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d2bbf7d4839d63b9f61159a6da8c902b86ed3d0d1ab0653ad09ff9936e7d825c","observation_id":"5351836b-be6c-4941-b63c-49fa8feb61d2","resolution":{"observed_at":"2026-07-03T02:07:33.483376Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Sok: Unintended interactions among machine learning defenses and risks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:650dd9d4d1fad9fa74367b212318b7c19c9b9c5bac9436d6197b78d85ad46ab1","observation_id":"440dbb3c-ecbc-4d40-9647-89e2f2b46b92","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Combining machine learning defenses without conflicts","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:7793eb076aeda5c3c3a830badb2029090ffe39bc7af6973ff3aab530fd2bfaa9","observation_id":"ad7dbdb0-dda7-4960-8278-840b47eec15f","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Gifd: A generative gradient inversion method with feature domain optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:51bcb4da2abc03d425f6c786e509d87a401b2251c77ca080fee900bb63156ba4","observation_id":"00e11ec3-ee6b-4261-8c5b-6d9bb295edcf","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14937","last_updated":"2024-02-22T19:44:19Z","snapshot_observed_at":"2026-08-03T09:46:52.837990Z","submitted_at":"2024-02-22T19:44:19Z","title":"SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge","version":1},"cited_work":{"arxiv_id":"2402.14937","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.14937","snapshot_observed_at":"2026-07-03T02:07:33.520220Z","title":"SoK: Ana- lyzing adversarial examples: A framework to study adversary knowledge","venue":null,"work_id":"6ce40c03-1c7b-4351-b5e0-21a6cf4f3c89","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2402.14937","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:49101cfc167f88e0d8c1aece8e0838a90cdd68007119898fdcc161ff427b9a2c","observation_id":"5dc27070-6650-4d75-84d6-6651e436afb3","resolution":{"observed_at":"2026-07-03T02:07:33.528004Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Stateful defenses for machine learning models are not yet secure against black-box attacks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:1b4985570eecd59f3f16f6b7a9dc6158e7254bbab402d3e13f74a255fd486d5a","observation_id":"cfe4c0ce-d005-461e-bec8-cbe292a86a75","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Privacy backdoors: Stealing data with corrupted pretrained models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:72dd1c823e15eeb539f5e378b30ea22352093c89cff362017466aa93201a5754","observation_id":"15a702ea-9744-4548-baf8-d0b6900e6606","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.16191","last_updated":"2023-12-22T08:11:33Z","snapshot_observed_at":"2026-07-06T17:08:12.928414Z","submitted_at":"2023-12-22T08:11:33Z","title":"SoK: Taming the Triangle -- On the Interplays between Fairness, Interpretability and Privacy in Machine Learning","version":1},"cited_work":{"arxiv_id":"2312.16191","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.16191","snapshot_observed_at":"2026-07-03T02:07:33.531941Z","title":"Julien Ferry, Ulrich Aïvodji, Sébastien Gambs, Marie-José Huguet, and Mohamed Siala","venue":null,"work_id":"f8796715-104e-44a7-ab8d-ad426288399b","year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2312.16191","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:b5e95f74ca9f310ae801f61ea104a8b3cab87bfa857c8ebaf6353463e01d001a","observation_id":"6fc98e72-f46a-4408-95ce-ac3d9d192f9d","resolution":{"observed_at":"2026-07-03T02:07:33.533423Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Differential privacy and fairness in decisions and learning tasks: A survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:af5bac196f5b3c0eeba35968adfe1043f17e6f44962d437e7a22f17ef57e537b","observation_id":"e3c8a585-c7d5-4543-92b1-8f8e6422b303","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Adversarial examples make strong poisons","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:407a0c4f76f5ecdf7d1fd105969eae19675cce9d62f6fbdb519252eb19bc0df3","observation_id":"9ffa44d6-603a-481c-8daa-d6f1761b88d6","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01686","last_updated":"2025-03-03T15:59:40Z","snapshot_observed_at":"2026-08-02T22:40:10.265668Z","submitted_at":"2025-03-03T15:59:40Z","title":"\\textsc{Perseus}: Tracing the Masterminds Behind Cryptocurrency Pump-and-Dump Schemes","version":1},"cited_work":{"arxiv_id":"2503.01686","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.01686","snapshot_observed_at":"2026-07-03T02:07:33.534464Z","title":"Perseus: Tracing the masterminds be- hind cryptocurrency pump-and-dump schemes.arXiv preprint arXiv:2503.01686, 2025","venue":null,"work_id":"884abdf9-54ff-4fdf-91c4-2a4c1c751ff0","year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2503.01686","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:7a21821657f40242228533fd8c18c15aee5386e111e8b2e9d82b2c6c0c31fb8c","observation_id":"80c76ff3-e26f-4a11-aa68-8d741a023142","resolution":{"observed_at":"2026-07-03T02:07:33.536434Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Un-fair trojan: Targeted backdoor attacks against model fairness","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:75ae17f3326544f673eef5165f0d6402797173474b56a664e11171c01735816c","observation_id":"32e42f91-17a7-43ca-80f1-797edfe5db2a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Bias and fairness in large language models: A survey.Computational Linguistics, pages 1–79, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:4863c1f7870b1f382a21bc96c66b81e26f86d515004355f805da6a97f6fc2365","observation_id":"6174c5d9-9fc0-49db-b117-3acbd9c2ea0d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Inverting gradients - how easy is it to break privacy in federated learning? InAdvances in Neural Information Processing Systems, pages 16937– 16947, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:9c83b3e19dfe54e266705ea4823ea13824892f51917faa65cb6b01e0f457ed5e","observation_id":"f7696123-16d4-4fb7-b2a9-026f498d9dd4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"An adversarial perspective on ac- curacy, robustness, fairness, and privacy: Multilateral- tradeoffs in trustworthy ml.IEEE Access, 10:120850– 120865, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:3853f6d6129f627e168c74c54e2a2d1e41965b5341a4dfdf4a3c6eb83e94fe08","observation_id":"f6e78812-2c76-4664-b0b6-6f8db1688647","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Inversenet: Augmenting model ex- traction attacks with training data inversion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d23603b0084c89f2b19228b002b1a53396ecc50cb160445ff0a1c32c1a2b31d9","observation_id":"56b52f6a-ce7d-490c-a9a4-d7b2b1abffc4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Adversarial initialization - when your network performs the way i want -.ArXiv e-prints, February 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:917a4a1be475129103ff8f26ad18b24e77c81a444f93e5af98a2353eca475a5c","observation_id":"0476a148-4da0-42e5-b71f-71054c6e3876","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"On the security relevance of initial weights in deep neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d1c474deed1553557cba028412012af906f8de168bbff706f8cfdb0bc26469d2","observation_id":"05c79a5c-0cdf-4bba-9c9f-35d26993334e","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"A survey on transferability of adver- sarial examples across deep neural networks.Transac- tions on Machine Learning Research (TMLR), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:b0e09548261e1100ac5c5d3575f29bd8fc8ec72b83df18fd5db9ac1f8e46a44b","observation_id":"b53e37b0-8b9e-4e9a-b437-492cc0c4c7cb","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"What is an initial access broker (iab)? Ac- cessed 2026-05-18","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:f79e74a933577b1f83223e251f599c209ce7d077583d6264d5afebb16b905b71","observation_id":"398bf5f1-b7e6-457f-91c8-484b36b429c5","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Reverse engineering convolu- tional neural networks through side-channel informa- tion leaks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:86b37dfab72538243ceaca1fd3327dea5e9d246b550e77fb0d2844abac7d6532","observation_id":"4dbea928-682d-4036-b19f-9bed4685ce8a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Are attribute inference attacks just imputation? InCCS, pages 1569– 1582, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:550970bda4cb8206047f23c824edf64d6d693cb2808900cfd40f1dab013833b2","observation_id":"da5d8684-ff5b-4b95-9701-02a77fd23f0f","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Adversarial robustness poisoning: Increasing adversarial vulnerability of the model via data poisoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:435251f67626ea3d6ada2688970e731c17b68a8dc6918036e5193d98e7d97e9a","observation_id":"fe4d982d-471a-4e92-98b9-b2eac3c96e14","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"TOGA: Trigger optimization for clean data ordering backdoor attack, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:bcd463532110f7f404566878f7d43d14f22ad308ff4b104367145f73d76a19d1","observation_id":"c9e732cf-4dec-4b99-bd8a-0fe0219e4e38","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Prada: protecting against dnn model stealing attacks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c487ff048ff2663b88d61e900d74ca437eecaba23f52ac2703a4522db3377d59","observation_id":"595a025a-9d97-473f-9a37-88edf5113186","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Thieves of sesame street: Model extraction on bert-based apis","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:cef993a357156dc0277f418a0fcd65dd7f92a22e36f0f8be733cc9edff746f8e","observation_id":"4c9344ef-83ad-4960-9a04-2ea0c79c55b2","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.18323","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T02:07:33.505899Z","title":"Architectural backdoors for within-batch data stealing and model inference manipulation","venue":null,"work_id":"6c46c3eb-e1ad-4539-9577-4a21a6d5c8a7","year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:87903011b255177b0c8f8cb5edd3d6f84ae4d611590b6086eb8c61acc7a40374","observation_id":"792d4dbc-14a4-4e26-b3db-64053fdd4662","resolution":{"observed_at":"2026-07-03T02:07:33.507383Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Architectural Neural Backdoors from First Principles","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d62e81079699145977dfa8fd130d131cf320853f1d0b92c6df461d27c463a75d","observation_id":"4a0a7d95-84bb-4130-ae8b-e5bbbda94eb5","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Enhanced label-only membership infer- ence attacks with fewer queries","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:0ec485831b390215ec2a9d6640d4cd6c8777587e73aeebea85dc2c27592f5e27","observation_id":"01b82c9e-ee9e-4c60-9198-cc8a6a6d443e","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Backdoor learning: A survey.IEEE Transactions on Neural Networks and Learning Sys- tems, 35:5–22, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:4991bb11bd1d1ecda9df46ad93b3b3060c52c17e86e0e0cf330f315b55a4ddd1","observation_id":"9ce2d6a3-8b0d-4d69-a92a-a90519ea5b52","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"From head to tail: Efficient black-box model inversion attack via long-tailed learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:bd8a52be6b4b79ba38181e28abfa17be6704d77138e8f42d4fb237969d6b7ba1","observation_id":"fd947e40-a1ac-42ee-8a47-a1485a78762e","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"{ML-Doctor}: Holistic risk assess- ment of inference attacks against machine learning models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:b966f16eb7e9ea6969d9d9c76f87eca3090b82340e5b725323a5bdfd6f680cd0","observation_id":"7e5fde8f-eb73-47d0-86d6-5a4c951c1026","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-07-06T21:46:30.250293Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"cited_work":{"arxiv_id":"2506.18870","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.18870","snapshot_observed_at":"2026-07-03T02:07:33.514395Z","title":"Amplifying machine learning attacks through strategic compositions","venue":null,"work_id":"45456ec0-e45c-4927-801d-bc9fc02e0ac2","year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2506.18870","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:6a910eedd58a0f4c85e28d92fc77a3d578bb119e68563a7444748ba2838db7a6","observation_id":"368abc4b-60de-4ff8-9534-f9692ef4c05b","resolution":{"observed_at":"2026-07-03T02:07:33.515930Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Stable bias: Evaluating societal representations in diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:8265a5269c519d26c2cbf762ead875661afc06fad9366655f614974fa967f3c5","observation_id":"c2910a79-971b-446c-bfa7-62dd35466045","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Analyzing leakage of personally identifiable information in language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:abe2daed33e54f29327ced4723f1574349ad54d6d1ad07d24b1fcf21d70e1d30","observation_id":"78f4500a-696f-4dd1-a113-fadbf39d2356","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Leveraging optimization for adaptive attacks on image watermarks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:6bb89e31bdbd8fda63ae8acf94cdf67cea22c4f5ffcbd7f0dee22d2441817323","observation_id":"eff825f2-14fb-4324-a553-1994126863ac","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Exploring privacy and fairness risks in sharing diffusion models: An adversarial perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:58f72614ce4c3952da3a80b0bdd5cbd9fc7a66ef2bcd0a7820b5cea9297b7372","observation_id":"170addc7-81c1-42bb-8d26-4a60262f2c2d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Deepstrike: Remotely-guided fault injection attacks on dnn accelerator in cloud-fpga","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:fce66b728fd91e84165f4261704dc0343803ab7c7a1787405e09ff97f29f9fa1","observation_id":"c5888f2a-969c-4235-ab6d-4031dfdbba61","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Honest-but-curious nets: Sensitive attributes of private inputs can be secretly coded into the classifiers’ outputs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:d92572c2d95fc51dae84942c67a50682f08b7a6dea5fcf6bb7586033b7ccd606","observation_id":"eb3e77e1-ffa9-4189-aa22-827037c3acff","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Eab-fl: Exacerbat- ing algorithmic bias through model poisoning attacks in federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:094a7f32af8c862c037389b0ad1ce9c88f9857d465a279ac38c990c481601418","observation_id":"f56ec576-769b-4b0f-9f75-8a8c2195ff06","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Exacerbating algorithmic bias through fairness attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:db8146471a875fe0950158f907c2471f2feb65ca5d8b4b856b3183ba8c3e800a","observation_id":"7bfdca2f-b85f-4aa0-8bf4-f396f955a4ca","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"A survey on bias and fairness in machine learning.ACM Comput","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:b3b6c9e1f96883675b36fc85b262fb20a1382b45086d796f60919b510cd3779a","observation_id":"b6d086ee-ba98-4d22-a56c-95c462f70d5b","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Exploiting unintended feature leakage in collaborative learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:7494c51ddd0a79e1877c130af52317a38043864f129a914f4e873759047d77f9","observation_id":"82e2622e-3e66-4a04-b6da-2ccd5b5e7e38","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.07968","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-03T02:07:33.508557Z","title":"From defender to devil? un- intended risk interactions induced by llm defenses","venue":null,"work_id":"52265528-0a67-4287-9681-d88cefb5c65a","year":2025},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:97044f82289d5c60e2ffc6470fdfc4e8fabd52a78ee34084b05c03ad0a7733ff","observation_id":"7c13b829-91c1-4de3-8368-9276701d80fb","resolution":{"observed_at":"2026-07-03T02:07:33.510156Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15213","last_updated":"2025-07-06T01:34:01Z","snapshot_observed_at":"2026-08-03T04:46:46.138220Z","submitted_at":"2024-06-21T14:53:19Z","title":"Backdooring Bias ($B^2$) into Stable Diffusion Models","version":4},"cited_work":{"arxiv_id":"2406.15213","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.15213","snapshot_observed_at":"2026-07-03T02:07:33.500381Z","title":"Backdooring bias into text-to-image models","venue":null,"work_id":"ca9082d1-4ac4-4be5-a3d0-99d52a8d6c75","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2406.15213","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:1826feb77f52e3ab2a458f103296d9f301e50def106c4c5ea38b6f2713e084e8","observation_id":"095fbd67-5052-42bb-bd2e-a5d5c70f5c98","resolution":{"observed_at":"2026-07-03T02:07:33.501984Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:351a40cd584b0181ee9f7963cbd47a1abde1432c4ac609e9f96d367d105fe579","observation_id":"3850608b-1038-47a8-ad0e-0d7af84dcab3","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Towards reverse-engineering black-box neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:95b5319a8519d0573622db725f5daa6b2a035ba27d7ad0ff2bfc1eeac2acd78e","observation_id":"0ee7eed7-e7b9-4def-a791-613009fd2074","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"I know what you trained last summer: A survey on stealing machine learning mod- els and defences.ACM Comput","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:8615cf0418d219063ee0c4769f183a8ef5757d4be9b7f1b41b0dcff75a9fe90a","observation_id":"09f729c2-8e51-48a5-b2bd-a2fbbf82ae8a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Knockoff nets: Stealing functionality of black-box models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:5c3c689f3e6bcbcdf516178a2d2a055d39828da859e0ada79c1b86ba87e388fd","observation_id":"57cdd9b3-2878-4290-9f24-7cd9cc4e78d6","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Teach llms to phish: Stealing private information from language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:e156ce5c7a99e70565faebdf87c9cc88a797b63ac15b24cdf5c23fcf441fae30","observation_id":"a9fda3b4-98f3-49cd-a984-6104cd637c12","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"A tale of evil twins: Adversarial inputs versus poisoned models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:9f23d5454b7b6c7822d8ae3e5d36b7fcfd8f86363fab4eb35fe6a4d573f9d821","observation_id":"5dc5f73c-c803-4913-a4f2-030ef0061f13","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Practical black-box attacks against machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c75c50b3666a04a4a203c4b61fd73496a964b4b963aa214fbedb866f67caa852","observation_id":"ea1c2aee-3812-4b39-ad25-10db6d822695","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"SoK: Security and privacy in machine learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:0c0575b61f6348772779dbd8ec962cb4db1b6229efc9f364255f13ccf2f1dd3e","observation_id":"7d41d056-13cc-4e10-8810-db6d31275ff4","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.01705","last_updated":"2025-03-30T01:49:11Z","snapshot_observed_at":"2026-07-06T19:44:34.642049Z","submitted_at":"2024-11-03T22:27:40Z","title":"Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors","version":2},"cited_work":{"arxiv_id":"2411.01705","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.01705","snapshot_observed_at":"2026-07-03T02:07:33.511366Z","title":"InProceedings of the Thirty-Ninth Annual ACM Symposium on Theory of Computing, STOC ’07, page 75–84, New York, NY , USA","venue":null,"work_id":"6bd4c354-aaf2-4593-a880-4554b2a67062","year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"cited_paper":"/paper/2411.01705","citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:09e7fafdc603e73aeb233e9e9d33adc910599d869c5cb1819fa5e497eb9c3dad","observation_id":"e279c1d2-a791-4d52-8969-6abb6c52eb70","resolution":{"observed_at":"2026-07-03T02:07:33.513230Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Circumventing concept erasure meth- ods for text-to-image generative models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:8da1b55d99668646de3c52719cc9f22636854357f691ab2c258e218881e38ab1","observation_id":"bc22d108-a81d-4d9d-a155-f8e128295b26","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Deep-Dup: An adversar- ial weight duplication attack framework to crush deep neural network in Multi-Tenant FPGA","venue":null,"work_id":null,"year":1919},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:79b288f1d95bcfcf471182c292c6a493933636a60253460a282f9d609101f3d4","observation_id":"c354ca72-86ee-4abe-a092-c7fba8277a3b","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"A survey of pri- vacy attacks in machine learning.ACM Comput","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:25f5be6132e855d401f2dba630b8d59d7242ed1644d16da80e65768829d4fc5c","observation_id":"ca779a1d-3a1e-43e0-bd06-f3f255a4e0c8","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Ml-leaks: Model and data inde- pendent membership inference attacks and defenses on machine learning models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:1bc9de34fbf0cc46a3c620e8ac53eb58f8e5a320557da3197359e5f7a9b1c7d5","observation_id":"90e99ce6-b783-4d78-8e18-be6496ad0516","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"SoK: Let the privacy games begin! a unified treatment of data inference privacy in machine learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:a2ae21bcb4b2abd54e936184ab53f4de79ebedcfe32d5687bf0008ad860db8bc","observation_id":"6c4c10fa-3b5c-4e0c-9e9f-dbbb0299363a","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:09afc3d3a6658b55c9c007932327f8f42c8b68dcb9d996184e9c5e021fdec912","observation_id":"d5f60409-13da-466f-ad12-3305d96abd3c","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Manipulating sgd with data order- ing attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:cea13cd09a0de1ebe2a2faf5810872d07e3ab721954db99ef4287dbe000ec4cc","observation_id":"e4f0d94f-1306-4ffb-89f6-e6f67a6fc13d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Sponge examples: Energy-latency attacks on neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:31aa23a712b7ccc95222689528499ed11594d0f9022addb44926dd15e73b78d3","observation_id":"0e2ef682-9e1b-4db0-ba08-d1c0341d0757","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Poisoning attacks on algorithmic fairness","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c261fa4fce205595135acb71341f80c001cee76717f9a936cc0c94f0939b3c1d","observation_id":"27942447-5050-478f-bfa1-54cc29e322f8","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Machine learning models that remember too much","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:931b12639983753ead21e032ebee9565483fc4b8c58799594db2bb0a6c227383","observation_id":"9bcaae46-72dc-49c0-b260-2ee215a93f9f","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Towards backdoor attacks and defense in robust machine learning models.Com- puters & Security, 127:103101, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:a84e3fe47b851a1bafcabc13c81b817f19a079a0c97f86f7e81f45a73ca00d68","observation_id":"d3fa7c80-b749-496e-9a5c-84148b8b19bc","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Strobel and R","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:4ea86110a562e5cb7b6cc6a4f9017d36cf5e0642b405d6f93bfb6dc09b192010","observation_id":"288bf692-6691-4ed4-adf4-2949bc9502e2","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Dissecting distribution inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:26fa4d1149b26abce076f9cdbb340bb9ff39d75f95ff9abbd9c9f7dd3ef32c4e","observation_id":"5233ab2a-dfa2-4283-a6b2-297377abc38f","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Formalizing and estimating distribution inference risks.PETS, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:ca30fb9bebe43b49a05ac1ed14cfd072e7543c394c924ddc287360f7662d372e","observation_id":"523ca1a0-9a48-4b44-8606-711d0c776db9","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"SoK: Pitfalls in evaluating black-box attacks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:c07f1888c905636a25adf18595b086e56745c850441182633b272cdfc081ad42","observation_id":"ffc7291c-e5e7-4cca-9ea2-3c75c87aa26d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Conflicting inter- actions among protection mechanisms for machine learning models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:9818cf90e83d2deabd558c61822d96f1a5c2f607a405e3db1d646891889b5496","observation_id":"a10b2eca-899b-40de-89af-506c23a1745d","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Manipulating Transfer Learning for Property Inference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:6cb14023093521a346b2b0a567e6611faf170255fc0577a7c018644a8afb487d","observation_id":"8b185338-970c-40b7-a0de-b7d41c6c8d70","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"Stealing machine learning models via prediction apis","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:358616bd6f1edd3b27242d53ea3f56a2cff6f230db4d8017908e6020c59c4807","observation_id":"900f3ccd-d75e-4475-bec2-51653f90e8cf","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T16:10:51.471822Z","title":"On adaptive attacks to adversar- ial example defenses","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-06-27T16:10:51.471822Z"},"links":{"citing_paper":"/paper/2606.10091"},"observation_digest":"sha256:1a8e5bedb2e6102484e9270fec340cce0d498735ba593652e967591592d62d3f","observation_id":"3b5108b1-4270-4160-97fe-f04d80e70e9b","resolution":{"observed_at":"2026-06-27T16:10:51.471822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.10091","last_updated":"2026-06-08T19:16:58Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-07-06T23:49:17.868841Z","submitted_at":"2026-06-08T19:16:58Z","title":"SoK: Colluding Adversaries in Machine Learning Pipelines"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":87,"verified_exact":11,"verified_fuzzy":0},"total_outbound_references":132},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 100 of 132 outbound references and 0 inbound Pith citation observations for arXiv:2606.10091."}