{"as_of":"2026-08-16T04:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34ab6a3f7ef594865107f79e61689cdd1441b6bfd75d9a92fd08ff1496321fb5","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:45:44.681189Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T16:10:51.471822Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T02:07:33.514395Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","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":"2026-08-05T00:07:01.562006Z","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":"sha256:2aa6c82ab70ad9067431e028dbcb17edae2f78a697f881b2c7328e9ca8891c0b","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 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.18870/citation-record","integrity":"/paper/2506.18870/integrity","json":"/paper/2506.18870/citation-record.json","paper":"/paper/2506.18870"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.629838Z","title":"Srivastava, and Kai-Wei Chang","venue":null,"work_id":"af48df4e-3aab-4684-98ff-dae9ff20d40b","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.398171Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:33c94d1808a007c811491023483e98edf862e7edd018b91315074aeea3d11a36","observation_id":"9b6449f1-8b08-466b-83a8-5ef0e4357a21","resolution":{"observed_at":"2026-08-15T18:45:45.634222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.616086Z","title":"Square Attack: A Query-Efficient Black-Box Adversarial Attack via Ran- dom Search","venue":null,"work_id":"6a2a2c8c-1715-45dc-ae67-a866379a5ab6","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.403823Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:548fe86fefb9cf82c0d6b2136c70959940a8e602394034f27a10df8c8aa9e927","observation_id":"b9705d72-0d4e-4a4e-8d65-ffa3afed267c","resolution":{"observed_at":"2026-08-15T18:45:45.620696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.601490Z","title":"PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable","venue":null,"work_id":"580ffe73-86f3-4556-88a6-e57b2e05aef8","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.408627Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:ecbec67aacc31c045171893a726211eb1ba6e67908e7be778a463ec9e64976d2","observation_id":"e718edcc-6a8b-45ed-9891-a0b483a491ab","resolution":{"observed_at":"2026-08-15T18:45:45.606346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.587051Z","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","venue":null,"work_id":"66428f62-8905-4b54-9b4b-babb62ad51e6","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.413337Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:91a566320ccb4579660a3b47248804d45883cdc38222c345ae1e58780ad1c09e","observation_id":"995ea52d-4cbc-484f-ab94-6296cb789856","resolution":{"observed_at":"2026-08-15T18:45:45.591823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.572872Z","title":"Freund, B","venue":null,"work_id":"d7af82e5-3e9c-4503-b1ee-9d7651d0a4d3","year":2011},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.418094Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:15ba165ae9f69baece27a634155aaf955de0a7280618d345d39fc4d578fccc2c","observation_id":"425decb7-9f24-4f1e-b5dd-2442cf901475","resolution":{"observed_at":"2026-08-15T18:45:45.577458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:45:44.422593Z","title":"Membership Inference Attacks From First Principles","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.422593Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:4414fb3edd66e3647e6a1c21dc56988cde2697d3f17bc3ab88db9582f604dd24","observation_id":"87b66152-6d79-4012-b95d-55d32dcfb350","resolution":{"observed_at":"2026-08-15T18:45:44.422593Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.550343Z","title":"Towards Evaluat- ing the Robustness of Neural Networks","venue":null,"work_id":"4cbddfb1-d011-4430-a4b3-11e3c4015e90","year":2017},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.426982Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:edc17760bbddf1656150d0c710b1afba625910fb5f41e8428d1f70066280975d","observation_id":"a514fa9f-61c7-47bd-ae59-e290dc2e57af","resolution":{"observed_at":"2026-08-15T18:45:45.554671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.535871Z","title":"Exclusionary Populism and Islamophobia: A comparative analysis of Italy and Spain.Religions,","venue":null,"work_id":"f495e313-b795-4b30-b73f-ace517e4d3b0","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.431415Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:10cd78bfcf303963ebc31db7ade0d9ba289711753bd08ec7833bf738fbefef62","observation_id":"b83b4011-60a7-495f-b56f-742bffeec01b","resolution":{"observed_at":"2026-08-15T18:45:45.540779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.521493Z","title":"GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models","venue":null,"work_id":"19f3bd37-0dcf-4862-9847-9c6a44624d6e","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.435731Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:dfa45cec9d397889f18ba4a4edde8709a4ae992274ce697ea49de1f60f341ade","observation_id":"d5286bc9-3e92-41f6-9bd8-d3a85adbb7aa","resolution":{"observed_at":"2026-08-15T18:45:45.526113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.507141Z","title":"Jordan, and Martin J","venue":null,"work_id":"f408c708-3a93-4336-a9dd-1fc5bba4cd8a","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.440535Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:d52f354fe1670091b4dea99a79a38e814e2331bcbaed912985cb9f9d0ebe7664","observation_id":"fa28d12f-2490-4b7a-9963-a94d95d898e8","resolution":{"observed_at":"2026-08-15T18:45:45.511821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.491561Z","title":"When Ma- chine Unlearning Jeopardizes Privacy","venue":null,"work_id":"dee6e195-42a6-4a58-b7b7-ccf08d51f8bc","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.444720Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:de46c2f368d40d9606a008e60311a6d74178b6827de063411bf9c0471c4438a7","observation_id":"c914f1e2-075c-4cf7-ad04-cbd6eafe1e2e","resolution":{"observed_at":"2026-08-15T18:45:45.496703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-15T18:45:44.449212Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning.CoRR abs/1712.05526, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.449212Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:d6aabd961fd7af274588faccbce17f2a76a9bf8994cfc0717647d43473da0ad5","observation_id":"95d5c54d-5c47-4144-99e9-2f285f63c512","resolution":{"observed_at":"2026-08-15T18:45:44.449212Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.477907Z","title":"Amplifying Membership Exposure via Data Poisoning","venue":null,"work_id":"62268ce1-8eee-4a68-8dec-96145f648166","year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.453732Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:77628a72612cce84475703b8905246f0d0a2384e60f59a3ef1c766c09d8bbf67","observation_id":"e53deeb5-32b0-493c-99e4-d2ff508355f8","resolution":{"observed_at":"2026-08-15T18:45:45.482298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.464554Z","title":"BERT: Pre-training of Deep Bidi- rectional Transformers for Language Understanding","venue":null,"work_id":"c5375e59-faf3-46ef-8fb5-2a35bce4b969","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.457967Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:0373546dccd2a345abac4f2e82b205d101c0597fe8fae666691725d1a68bb1b9","observation_id":"923d65bd-6ba5-494a-a4b1-32fad29ccdc5","resolution":{"observed_at":"2026-08-15T18:45:45.468995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.450714Z","title":"Now Publishers Inc., 2014","venue":null,"work_id":"59928f0c-b195-4e44-8a6f-59ac954f44a7","year":2014},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.462105Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:b605f8b38bae9b82f7980e99a917b7cc3a24e3d3aef66558c9d730e2978488d1","observation_id":"141d77ca-f6e4-4115-bd12-51f83b0105c5","resolution":{"observed_at":"2026-08-15T18:45:45.454857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06062","last_updated":"2024-11-26T03:19:15Z","snapshot_observed_at":"2026-08-13T05:28:26.446906Z","submitted_at":"2023-11-10T13:55:05Z","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06062","snapshot_observed_at":"2026-08-15T18:45:44.466422Z","title":"Practical Membership Infer- ence Attacks against Fine-tuned Large Language Mod- els via Self-prompt Calibration.CoRR abs/2311.06062,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.466422Z"},"links":{"cited_paper":"/paper/2311.06062","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:b0aba24ffceba86e6ee05279c58d89626040e194cc64e399002d89f3c78658da","observation_id":"9e082dc9-4834-462b-a2ad-82fba7c9771c","resolution":{"observed_at":"2026-08-15T18:45:44.466422Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.437498Z","title":"Gunter, and Nikita Borisov","venue":null,"work_id":"36e36062-72d4-4ab7-8438-a1f09ccc129f","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.471090Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:7f1fc3ee0b755bdf807324cc0a27eb19df12179354b58140a6a4cf16894e5835","observation_id":"3ec5cb4e-0b43-4603-ac94-21e4bad63c55","resolution":{"observed_at":"2026-08-15T18:45:45.441743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.423174Z","title":"Explaining and Harnessing Adversarial Ex- amples","venue":null,"work_id":"9ba08803-00e1-423e-836c-1a75f5146818","year":2015},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.475367Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:99ce90ed846527473a757d1dcf4acfa6bcc37aad3679df59131f5a5ce6a8bb4e","observation_id":"73f03b2e-76f1-461b-85e0-f3621f0a5004","resolution":{"observed_at":"2026-08-15T18:45:45.427910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-15T18:45:44.479739Z","title":"Badnets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.CoRR abs/1708.06733,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.479739Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:1e14fb4826c805cfd40c62fedbbbce65e8885ff9bc2702120d3bfa547b997f80","observation_id":"a774c37c-0429-4507-82e2-03554ca3b867","resolution":{"observed_at":"2026-08-15T18:45:44.479739Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.408017Z","title":"Deep Residual Learning for Image Recognition","venue":null,"work_id":"254fa8b7-7cd9-49ac-b261-7afde40f5176","year":2016},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.484766Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:35cd77a5fbfb69ace6609c5115c88d3e567ea42e522dbe6abf24ae6e4f19bf39","observation_id":"5e0232bf-d360-48a6-8356-97d793268cd2","resolution":{"observed_at":"2026-08-15T18:45:45.412851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.10445","last_updated":"2022-08-22T17:00:53Z","snapshot_observed_at":"2026-08-13T16:18:59.537726Z","submitted_at":"2022-08-22T17:00:53Z","title":"Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.10445","snapshot_observed_at":"2026-08-15T18:45:44.489213Z","title":"Membership-Doctor: Comprehensive As- sessment of Membership Inference Against Machine Learning Models.CoRR abs/2208.10445, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.489213Z"},"links":{"cited_paper":"/paper/2208.10445","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:6d217b2364284fb94ec7cf370b40ae0f1e7f148442d9eee68509b7fa9a5ebfd2","observation_id":"c0e2748c-20bf-411d-8c02-acdca6d44a1e","resolution":{"observed_at":"2026-08-15T18:45:44.489213Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.394147Z","title":"Quantifying and Mitigat- ing Privacy Risks of Contrastive Learning","venue":null,"work_id":"d978e899-66b1-43a0-b240-61e561838e54","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.494411Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:75cb1d0a79bb1c4101de2a4403f20790d578dbeb124518e7605c6ba28d424f4d","observation_id":"0924082b-9e8a-4a35-a82d-09a6fe7a6976","resolution":{"observed_at":"2026-08-15T18:45:45.398676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.380156Z","title":"Weinberger","venue":null,"work_id":"e51ddf85-7013-4c4b-b13a-022915acab36","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.498855Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:bc0a2d37dcfe5f017a0df08b775c7aeb18637e885117f654fc3a08f6e78c3625","observation_id":"153b2c54-76de-4050-ad3d-b3b269ae1ece","resolution":{"observed_at":"2026-08-15T18:45:45.384862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.366093Z","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","venue":null,"work_id":"cd54e8e3-bb21-44d7-9bd7-276522bbe5c5","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.503382Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:a93922cc55d88e3b6ae9b36499348973efefe45d0d86c6667a58f99705f30928","observation_id":"f3211609-477f-4999-a729-41f59dd1959f","resolution":{"observed_at":"2026-08-15T18:45:45.371013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.352708Z","title":"Evaluating Differentially Private Machine Learning in Practice","venue":null,"work_id":"8cc3dabd-3fc5-4d7c-90cc-e67e31ae8cee","year":1912},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.507620Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:9e631da144f83eced8148d6dc40f5f7439f39082ee6f1537f2052564e1966dc1","observation_id":"729559f3-9705-468d-99b2-50ba50b36b96","resolution":{"observed_at":"2026-08-15T18:45:45.357186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.338463Z","title":"MemGuard: De- fending against Black-Box Membership Inference At- tacks via Adversarial Examples","venue":null,"work_id":"97d0e24b-370d-491a-af8c-6abe385664d9","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.511781Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:11c0bfc9573d9a0a60be5606850aec00c826a4c9bfd386421515f5fb71893e51","observation_id":"111d6d3e-ddb1-46b0-a2eb-f497eb2d4561","resolution":{"observed_at":"2026-08-15T18:45:45.342998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.324052Z","title":"Seitz, Daniel Miller, and Evan Brossard","venue":null,"work_id":"f6d4fe0d-4588-43fe-9f67-9c4d77586f0b","year":2016},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.515970Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:a9a9ebf5980f0126f28b56379ef19bb6966bcf7a01197a95979d555b7de3789d","observation_id":"d2546001-96ba-40b7-9b9f-03ff439b795c","resolution":{"observed_at":"2026-08-15T18:45:45.328789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.310142Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":"1669bf7b-2b6d-4e37-be55-7a9945aeb50d","year":2015},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.520343Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:d3b0ecdcff3db6876c94985799e3992b11f2ee85853138fa1446b9ba79a4a866","observation_id":"19ad8e23-52cd-4204-a965-23a89fe0266b","resolution":{"observed_at":"2026-08-15T18:45:45.314734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.294741Z","title":"Exarchos, Konstanti- nos P","venue":null,"work_id":"68db5205-3cc3-42db-a2d4-81b4eeaf69d8","year":2015},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.524530Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:b0bd8a793a6a43ad0e8636ab095a5938c5c69763e51f8712e8194b159e9f0715","observation_id":"19936014-15a1-4006-bb9c-17dba34eb50a","resolution":{"observed_at":"2026-08-15T18:45:45.299386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.279690Z","title":"Stolen Memo- ries: Leveraging Model Memorization for Calibrated White-Box Membership Inference","venue":null,"work_id":"09ae8108-6774-4a7e-abbe-78d8c606d4c1","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.528671Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:c7c75473880340048d6f306a8f88de7aefc3f1f72faf8700bd1d793bbc0ceece","observation_id":"4450d696-6a4b-443d-893b-ae0d1b4b5af6","resolution":{"observed_at":"2026-08-15T18:45:45.284827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.264522Z","title":"QEBA: Query-Efficient Boundary-Based Blackbox Attack","venue":null,"work_id":"cc62eaff-bf49-424f-a9d3-cb024e87d2aa","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.532667Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:10406cbb12bdf442845f818bd7e5dc25291f465a144bf9bc1ae3be66ef5a0a03","observation_id":"a447d50f-cbd3-4344-8971-a040cfd6fca3","resolution":{"observed_at":"2026-08-15T18:45:45.269235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.249587Z","title":"Morgan & Claypool Publishers, 2016","venue":null,"work_id":"33c605a7-fe6a-4220-ac71-11580a642f19","year":2016},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.536860Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:339c247c56ecac7546659478019316464970ed854bbcd378664d2c5bea927277","observation_id":"0b30deed-8400-47c3-87cd-20cf6f636999","resolution":{"observed_at":"2026-08-15T18:45:45.254008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.11180","last_updated":"2022-08-23T20:16:19Z","snapshot_observed_at":"2026-08-13T14:40:03.731669Z","submitted_at":"2022-08-23T20:16:19Z","title":"Auditing Membership Leakages of Multi-Exit Networks","version":1},"cited_work":{"arxiv_id":"2208.11180","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.11180","snapshot_observed_at":"2026-08-15T18:45:44.787306Z","title":"Auditing Membership Leakages of Multi-Exit Networks","venue":"cs.CR","work_id":"9fb63a1b-fcf0-4e3c-a904-42bf075164b1","year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.540781Z"},"links":{"cited_paper":"/paper/2208.11180","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:83917462c9e542d5dd5dbc124b07c247b02a00d677bedb0adfcd61693535c33d","observation_id":"535ec106-3102-44ed-a22f-4f12cea0ed54","resolution":{"observed_at":"2026-08-15T18:45:44.794263Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.234787Z","title":"Auditing Membership Leak- ages of Multi-Exit Networks","venue":null,"work_id":"b56b0f5e-3d0d-47ae-9f64-6e29d4dd39a1","year":1917},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.545357Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:ae11e1d4e0996176045075b4de2c04b42d593470f9cde46c78ed74a9dd885ad0","observation_id":"9df48682-0a01-47aa-89a9-0057ab92648f","resolution":{"observed_at":"2026-08-15T18:45:45.239686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.220012Z","title":"Membership Leakage in Label-Only Exposures","venue":null,"work_id":"4e51142d-0434-4af3-ac15-fbae6bd97873","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.549456Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:b85f72a9c5b8a2dfe8b27f612938c6360bdda690e75f28b001154971ae496579","observation_id":"b4240e74-5f93-4c65-a663-6fb83d03f4ae","resolution":{"observed_at":"2026-08-15T18:45:45.224841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.206070Z","title":"DEEPSEC: A Uniform Platform for Security Analysis of Deep Learn- ing Model","venue":null,"work_id":"8e9ff285-465f-491d-8139-9e9b5788708a","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.553683Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:cc3f14ebf4362d1d38594ee0feb6a6f71b5c870606f05ebff9d6a213694f63ec","observation_id":"82e391b1-956e-40ff-9ac9-fcde1607957f","resolution":{"observed_at":"2026-08-15T18:45:45.210683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.191364Z","title":"Trojaning Attack on Neural Networks","venue":null,"work_id":"46d36e01-79a0-4d4a-931c-636ce243cb6a","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.558074Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:6a926ebfa482b5baa422ee860ac40579c012e3c02d7d4579ec35a782271d5181","observation_id":"bd443869-0b42-481e-a1d1-ba389dd12132","resolution":{"observed_at":"2026-08-15T18:45:45.196336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.14933","last_updated":"2022-08-31T16:02:26Z","snapshot_observed_at":"2026-08-14T15:46:55.635944Z","submitted_at":"2022-08-31T16:02:26Z","title":"Membership Inference Attacks by Exploiting Loss Trajectory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.14933","snapshot_observed_at":"2026-08-15T18:45:44.562171Z","title":"Membership Inference Attacks by Exploiting Loss Trajectory.CoRR abs/2208.14933, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.562171Z"},"links":{"cited_paper":"/paper/2208.14933","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:4ff97ce477f9f5db74b5459067f1b6c5436e4994ba977a2fb90df23160928e7c","observation_id":"c4ac40b1-f3b9-4b0a-ba13-dc59628bf980","resolution":{"observed_at":"2026-08-15T18:45:44.562171Z","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":"2026-08-15T18:45:44.566716Z","title":"ML-Doctor: Holis- tic Risk Assessment of Inference Attacks Against Ma- chine Learning Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.566716Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:b44798332a56e20475d9ff22736678f2685fcfc93d43f81ea6b11f42a52d459c","observation_id":"4fea5b69-71d3-4756-8382-3abf287af98c","resolution":{"observed_at":"2026-08-15T18:45:44.566716Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.166982Z","title":"Deep Learning Face Attributes in the Wild","venue":null,"work_id":"515e1410-ee3d-4551-b82a-085d5e7f7b8a","year":2015},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.570845Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:572d8c67596ef89f549e76e525a1d4a18a44e78b29c9f79f8b6741e3f13ff3f8","observation_id":"60957317-7ca4-4117-beec-10aecc2cbe94","resolution":{"observed_at":"2026-08-15T18:45:45.171586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.152725Z","title":"To- wards Deep Learning Models Resistant to Adversarial Attacks","venue":null,"work_id":"6cd2f7b5-9fe6-4279-bd17-b31e9820fe54","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.574821Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:5fe13a766ad220ec17b572f95362673d547b4ccd1c26cc62ca5c3c5c124cddf5","observation_id":"f2a74b41-bdb2-42c6-83e3-e448cccbb75a","resolution":{"observed_at":"2026-08-15T18:45:45.157680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.138198Z","title":"Property Inference from Poisoning","venue":null,"work_id":"000bed12-c8cb-4600-b196-f8ccfce4bbd3","year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.579181Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:8f1198c7d7d03201301d047f69bddbcb11f3addde003ab3b91107ca9ff27aa66","observation_id":"83d10d5a-4df7-439b-9cc9-bc8ad0536771","resolution":{"observed_at":"2026-08-15T18:45:45.142987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.124082Z","title":"Exploiting Unintended Feature Leakage in Collaborative Learning","venue":null,"work_id":"e7daf940-2b46-48d7-8d90-be611ea85868","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.583380Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:c356a907b73d0f2519d6741fdac8d3bff28a09c82997e332c4b744fc20e142ea","observation_id":"59a99784-167e-465d-b8a9-1bf5a2311ac5","resolution":{"observed_at":"2026-08-15T18:45:45.128730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.109725Z","title":"Ma- chine Learning with Membership Privacy using Adver- sarial Regularization","venue":null,"work_id":"fd1a9d35-f99c-4426-9c69-dc4858faabb5","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.587943Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:2dc22f067e26d2999eda1a6fbfe047a497fdd454bec51a0224dca3f1815e8920","observation_id":"dc8c072f-693e-4a6f-9061-abab2ffb25c5","resolution":{"observed_at":"2026-08-15T18:45:45.114242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.095439Z","title":"Com- prehensive Privacy Analysis of Deep Learning: Pas- sive and Active White-box Inference Attacks against 15 Centralized and Federated Learning","venue":null,"work_id":"23d023fb-1d38-4657-92ad-b1d16a860ada","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.592553Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:505fd342f3831648516785d88a84636a3a7cf2cb473f1a254a5e8555ed5a47b4","observation_id":"0f6b889a-3b79-4f55-9766-3ff0107dddf3","resolution":{"observed_at":"2026-08-15T18:45:45.099997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.080887Z","title":"Adversary Instanti- ation: Lower Bounds for Differentially Private Machine Learning","venue":null,"work_id":"f5caf5e3-f450-47c3-9b55-e710bebdb538","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.596916Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:56903799632e30330fed1c39590dd85eed0891c0f926cf81264682aeb6b688f9","observation_id":"9afbc8c4-dd2b-471f-a818-a3d4d3f20a90","resolution":{"observed_at":"2026-08-15T18:45:45.086107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.09302","last_updated":"2022-10-21T06:29:19Z","snapshot_observed_at":"2026-07-06T10:25:14.308394Z","submitted_at":"2020-12-16T22:37:27Z","title":"TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.09302","snapshot_observed_at":"2026-08-15T18:45:44.601353Z","title":"TROJAN- ZOO: Everything You Ever Wanted to Know about Neural Backdoors (But Were Afraid to Ask).CoRR abs/2012.09302, 2020","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.601353Z"},"links":{"cited_paper":"/paper/2012.09302","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:3caa791cf11162bf9a1b5f4c56d6f381b097411445b60caf283c149d72b19cc5","observation_id":"66ce2715-0247-42ce-b1b6-2ef9d53cb463","resolution":{"observed_at":"2026-08-15T18:45:44.601353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.00768","last_updated":"2018-06-27T21:06:06Z","snapshot_observed_at":"2026-08-14T21:36:55.675026Z","submitted_at":"2016-10-03T22:04:07Z","title":"Technical Report on the CleverHans v2.1.0 Adversarial Examples Library","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.00768","snapshot_observed_at":"2026-08-15T18:45:44.605719Z","title":"Technical Report on the CleverHans v2.1.0 Adversarial Examples Library.CoRR abs/1610.00768, 2018","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.605719Z"},"links":{"cited_paper":"/paper/1610.00768","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:08827c3a3ebb0e91003500243cd9ef2cda39dccf99e398e1a9f991e4b1548c25","observation_id":"fe2b2fef-2215-4f59-af03-207b0723768a","resolution":{"observed_at":"2026-08-15T18:45:44.605719Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.066684Z","title":"McDaniel, Somesh Jha, Matt Fredrikson, Z","venue":null,"work_id":"50bed20e-1eda-431e-8715-3ca167fc2940","year":2016},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.610397Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:2130f2755aea9bc98a564d0ab0122ea9676ab99b087821b10fb0e8d04706a474","observation_id":"92f0d8ce-f5d1-4396-832b-22efe904d0c1","resolution":{"observed_at":"2026-08-15T18:45:45.071433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.052474Z","title":"Semantically Equivalent Adversarial Rules for Debugging NLP models","venue":null,"work_id":"dff7ed8d-a60b-4687-8d09-544a0bf0579e","year":2018},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.614691Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:4bf00c41ed650b49411ccaeb8bbfbbd9ec07d63423fc8e2c079eb82c4547e0f7","observation_id":"12ed3e02-ff3b-4866-afa7-0f97e35698be","resolution":{"observed_at":"2026-08-15T18:45:45.056906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.038379Z","title":"White-box vs Black-box: Bayes Optimal Strategies for Membership Inference","venue":null,"work_id":"4fe8c085-90a1-4403-a1e0-f1051640f454","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.619188Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:03ce4015d89223dbb5cab9bfd1a498931572692cf65ab72ccdc7e69e92bff1a3","observation_id":"75533ef2-c9c5-4815-9255-e89aad238cb7","resolution":{"observed_at":"2026-08-15T18:45:45.043090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.024032Z","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","venue":null,"work_id":"18020c83-331b-41f4-912a-0f6dff00ba17","year":2019},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.623665Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:e5ae8cb8f6faff9f5bb61ccb54f6620a92b456ddaf036f7385fc51265053dbf1","observation_id":"c270c1f6-0563-4ef8-83f3-d40b3653f7e7","resolution":{"observed_at":"2026-08-15T18:45:45.028719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:45.009715Z","title":"Membership Inference Attacks Against Machine Learning Models","venue":null,"work_id":"ec43232f-34b8-418d-b5e1-422c9317fc7c","year":2017},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.627833Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:1c0139a01309da78d50a1534c640f8362d3e5debb3f3006d2d03e3f71aa61d7b","observation_id":"87825be1-987b-485a-85f0-f0913c38e55b","resolution":{"observed_at":"2026-08-15T18:45:45.014351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.994742Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recog- nition","venue":null,"work_id":"c799e208-ec72-4685-801c-f347e7dc6f90","year":2015},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.632145Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:c3405631baabd23d927c2332d83fcb47ab180189c0617e7ea98469de242d37da","observation_id":"1888a72c-8dff-437f-bb2a-fee02756d933","resolution":{"observed_at":"2026-08-15T18:45:44.999413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.980233Z","title":"Overlearning Reveals Sensitive Attributes","venue":null,"work_id":"419ebe20-2f08-4900-b571-4d6d79a2853d","year":2020},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.637128Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:d5ff777e063aad70f2da5bbe12f86249f921996910714485f79384e48ea059e6","observation_id":"fb08c8cc-f71b-45eb-b6b0-8101014a7d04","resolution":{"observed_at":"2026-08-15T18:45:44.985257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.965759Z","title":"Stanfill, Margaret Williams, Susan H","venue":null,"work_id":"e8372051-a8c0-4d2f-924d-f753c4cfd532","year":2010},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.641900Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:45448e32ada1f511f2225f58ff9505b7cd3c113b9681769533bf11713331a2b8","observation_id":"83ba3dcd-f558-4370-9e4a-7a602049e847","resolution":{"observed_at":"2026-08-15T18:45:44.970237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.951251Z","title":"Intriguing Properties of Neural Networks","venue":null,"work_id":"1cabe7ae-425c-405c-a860-e82f59ea23fb","year":2014},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.646364Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:be0785e0ee35b59ab5925e734c2fc2ac6439a3d8af52bbc66cefb22ce0195ab7","observation_id":"ddf473c2-f533-460c-8967-35719f5dd6d2","resolution":{"observed_at":"2026-08-15T18:45:44.956329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01231","last_updated":"2024-04-01T16:50:54Z","snapshot_observed_at":"2026-08-13T00:39:58.740217Z","submitted_at":"2024-04-01T16:50:54Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01231","snapshot_observed_at":"2026-08-15T18:45:44.650820Z","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models.CoRR abs/2404.01231,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.650820Z"},"links":{"cited_paper":"/paper/2404.01231","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:f3e2bf86f4fbcb568d069dd5a27edd03258b0dee11209fee9e547da058dac14a","observation_id":"18759f41-9b02-4357-811d-810b0f986e05","resolution":{"observed_at":"2026-08-15T18:45:44.650820Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.937139Z","title":"Gunter, and Bo Li","venue":null,"work_id":"2e3efaee-8af6-4e7e-a72b-d1e5324f5b71","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.655420Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:4aaeeca1452fbb3d89e91a50a3ee0b2174e8930fc5150135155ec7ea24877554","observation_id":"d110ad2e-8ad7-4609-94ea-7dcd0c3439f9","resolution":{"observed_at":"2026-08-15T18:45:44.941619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.921603Z","title":"Se- curityNet: Assessing Machine Learning Vulnerabilities on Public Models","venue":null,"work_id":"ff8be946-6a23-4df2-a63f-6613e1447112","year":2024},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.659985Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:1680817aafb7cb879ea7dad49ec049a41422f3b319dee720682f130e2145a4c2","observation_id":"6e5aad50-5ed8-48a7-86c3-763cb1ac64f7","resolution":{"observed_at":"2026-08-15T18:45:44.926367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.905987Z","title":"Membership Inference Attacks Against Recommender Systems","venue":null,"work_id":"87562d84-2041-41f6-8193-4647088da1db","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.664193Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:c9a1c260f231f249844be420c3f8384f46223bb9ffa097996139104c9ea92527","observation_id":"50801164-5108-47e0-baa5-6a5e71903723","resolution":{"observed_at":"2026-08-15T18:45:44.910989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.890576Z","title":"ViT-YOLO: Transformer- Based YOLO for Object Detection","venue":null,"work_id":"b7010ba5-033f-42cc-8637-25a96ecf9fba","year":2021},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.668148Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:3680261377febe8337914402d202ffc04bedbe8c27646ad458d57e65ccdb7ad6","observation_id":"382b5cad-6be1-464f-ace2-f0397f024be4","resolution":{"observed_at":"2026-08-15T18:45:44.895617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.08197","last_updated":"2017-08-28T06:07:27Z","snapshot_observed_at":"2026-08-14T20:38:39.875067Z","submitted_at":"2017-08-28T06:07:27Z","title":"Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.08197","snapshot_observed_at":"2026-08-15T18:45:44.672442Z","title":"Cross- Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments.CoRR abs/1708.08197, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.672442Z"},"links":{"cited_paper":"/paper/1708.08197","citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:e8b2371d7243484f5d9a5dbec32bccb88f43a964b718ec650fe5ab5437735b35","observation_id":"9903b9be-635e-40f3-a26f-e086164fff6d","resolution":{"observed_at":"2026-08-15T18:45:44.672442Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.872794Z","title":"Places: A 10 Million Image Database for Scene Recognition.IEEE Trans- actions on Pattern Analysis and Machine Intelligence,","venue":null,"work_id":"577eab89-ab4d-46c4-a46e-bdda0c2e6a85","year":null},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.676914Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:4010bbd22f19b9648f838e2d879837267529d5c9a93dba2f2788574aadb76d91","observation_id":"09043879-cfd5-4d8a-a549-56853915fc1d","resolution":{"observed_at":"2026-08-15T18:45:44.877905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:45:44.858338Z","title":"Property Inference Attacks Against GANs","venue":null,"work_id":"c346518b-455a-4eac-b1a6-57e15c70e186","year":2022},"citing_paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-15T18:45:44.681189Z"},"links":{"citing_paper":"/paper/2506.18870"},"observation_digest":"sha256:3def39fe644c10878cef37762d01d9f014a3896fcdf06b5f6b1b76a5d6b9e712","observation_id":"c9755593-b411-4189-9837-3181bb223723","resolution":{"observed_at":"2026-08-15T18:45:44.862915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.18870","last_updated":"2025-06-23T17:38:48Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-15T18:39:24.635694Z","submitted_at":"2025-06-23T17:38:48Z","title":"Amplifying Machine Learning Attacks Through Strategic Compositions"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":53},"total_outbound_references":65},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 1 inbound Pith citation observation for arXiv:2506.18870."}