{"as_of":"2026-08-10T23:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7095650db0b719485de974911b18210acaeac8ba658235e8c177329755913fdc","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:19:48.353611Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:46:59.087462Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.08862","snapshot_observed_at":"2026-08-06T04:46:59.087462Z","title":"Armor: Shielding unlearnable examples against data augmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.03091","last_updated":"2025-08-05T05:10:14Z","snapshot_observed_at":"2026-08-08T11:47:13.622459Z","submitted_at":"2025-08-05T05:10:14Z","title":"T2UE: Generating Unlearnable Examples from Text Descriptions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T04:46:59.087462Z"},"links":{"cited_paper":"/paper/2501.08862","citing_paper":"/paper/2508.03091"},"observation_digest":"sha256:615cf3d341ab4f3f1b5780f924785aa1334b7928c60d6916747687c0c8423f81","observation_id":"a2f30960-d311-457e-97e2-8dcd1286bc8a","resolution":{"observed_at":"2026-08-06T04:46:59.087462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"cited_work":{"arxiv_id":"2501.08862","doi":"10.48550/arxiv.2501.08862","metadata_source":"arxiv_reference","pith_arxiv_id":"2501.08862","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"ArXiv.org","work_id":"f5b62eaa-8be6-4ec0-9633-fda76373dcc4","year":2025},"citing_paper":{"arxiv_id":"2605.11592","last_updated":"2026-05-12T06:17:13Z","snapshot_observed_at":"2026-07-06T23:23:26.077921Z","submitted_at":"2026-05-12T06:17:13Z","title":"SoK: Unlearnability and Unlearning for Model Dememorization","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-13T01:43:44.193175Z"},"links":{"cited_paper":"/paper/2501.08862","citing_paper":"/paper/2605.11592"},"observation_digest":"sha256:80f18280b3246066e90ee01226c962247b2c2a7805d5f063c8eb94cc21114c79","observation_id":"a9081433-8a96-4941-9378-6912f1c958c8","resolution":{"observed_at":"2026-05-13T01:47:04.283258Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"cited_work":{"arxiv_id":"2501.08862","doi":"10.48550/arxiv.2501.08862","metadata_source":"arxiv_reference","pith_arxiv_id":"2501.08862","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"ArXiv.org","work_id":"f5b62eaa-8be6-4ec0-9633-fda76373dcc4","year":2025},"citing_paper":{"arxiv_id":"2605.12792","last_updated":"2026-05-12T22:10:01Z","snapshot_observed_at":"2026-07-06T23:24:27.821980Z","submitted_at":"2026-05-12T22:10:01Z","title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-14T20:41:10.931383Z"},"links":{"cited_paper":"/paper/2501.08862","citing_paper":"/paper/2605.12792"},"observation_digest":"sha256:cc94a56577854c24558f49daef1addd2bd9b009156cbf9d6960a0e63ada21d00","observation_id":"7b81f646-7865-4ed5-a66f-1a0cdbfae475","resolution":{"observed_at":"2026-05-14T20:42:56.162356Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.08862/citation-record","integrity":"/paper/2501.08862/integrity","json":"/paper/2501.08862/citation-record.json","paper":"/paper/2501.08862"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:19:49.158156Z","title":"Privacy-preserving machine learning: Threats and solutions","venue":null,"work_id":"6af1ce92-fb6c-49e1-9bac-bc21bf965a27","year":2019},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.106479Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:74490d6b42d58a0c5bbede57d69afbee7ea3125c0b9a5f6c5fa554c3e9d0f36e","observation_id":"92b17d5d-b8cc-46af-9bab-920eb86c7492","resolution":{"observed_at":"2026-08-10T20:19:49.162908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.144732Z","title":"Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff","venue":null,"work_id":"ff1ddd03-7f5c-4922-a3de-02742f7b973f","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.111671Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:fd81f90798857f44d60a2f2e90f6009fd95b56025eb14c8b71d997d4ce1bb2c8","observation_id":"2f3272a2-f2b4-4786-91b5-68d7820efd7e","resolution":{"observed_at":"2026-08-10T20:19:49.149242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.129469Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"7acb54b2-144e-4795-824f-0f228a676e2a","year":1914},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.116205Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:ab48087dd2ed2eb2cc131adc1617f895eccfbf96201a3d03bcf4819fe9e62984","observation_id":"fee88e4f-3093-400e-85ae-5a117add62dd","resolution":{"observed_at":"2026-08-10T20:19:49.134370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.115554Z","title":"A group-theoretic framework for data augmentation","venue":null,"work_id":"64c081cd-8959-41ea-8890-ff0c01275531","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.120962Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:0acfe324c4112abd67dff242b9be8c25aef25c8b7f3745667ad3d6839a3299b5","observation_id":"37c2f71c-cdbf-4d84-b8b7-f056e58ca26a","resolution":{"observed_at":"2026-08-10T20:19:49.120474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.07922","last_updated":"2021-01-25T04:23:22Z","snapshot_observed_at":"2026-08-10T04:23:47.327572Z","submitted_at":"2021-01-20T01:40:06Z","title":"LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.07922","snapshot_observed_at":"2026-08-10T20:19:48.125387Z","title":"Lowkey: Leveraging adversarial attacks to protect social media users from facial recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.125387Z"},"links":{"cited_paper":"/paper/2101.07922","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:ecc4d5a90a0abd504597e7644abd36fe2d379c3bce9453efdac1df2f33a91c4d","observation_id":"5c7ffd01-05cc-40a1-9c55-072718a736f6","resolution":{"observed_at":"2026-08-10T20:19:48.125387Z","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":"2026-08-10T20:19:49.101283Z","title":"Autoaugment: Learning augmentation strategies from data","venue":null,"work_id":"75a76d44-cf71-4209-a432-b31c9a9b43f9","year":2019},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.130102Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:b97da9a5026fb519da734b02088da5629ad23d6a3b55e52e7233184097866c7b","observation_id":"89bc0cb1-cce0-4dd1-9bee-cf33547b1d8d","resolution":{"observed_at":"2026-08-10T20:19:49.106206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.086786Z","title":"Ran- daugment: Practical automated data augmentation with a reduced search space","venue":null,"work_id":"1f1426bc-7302-41ee-9a6e-040db0018f5f","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.134949Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:15aa19e28897d8b91b2a5e8c0692b633e28737ad0f97a0f0b09138f224f022a2","observation_id":"e5e5b051-83f3-4a3f-88f8-631ac6bce115","resolution":{"observed_at":"2026-08-10T20:19:49.091948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.073122Z","title":"Imagenette: A smaller subset of 10 easily classified classes from imagenet","venue":null,"work_id":"1600cb2e-16cd-45d2-9350-3688f23fc12b","year":null},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.139223Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:b1b190092bc2ff7da99fb8ba582f437473011c2e0beb1ea1311b9572482f7c66","observation_id":"9b1e5804-0ab5-4e9d-91e9-d9fcdcd2a95b","resolution":{"observed_at":"2026-08-10T20:19:49.078275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.02683","last_updated":"2021-03-05T04:55:01Z","snapshot_observed_at":"2026-07-06T10:46:37.326040Z","submitted_at":"2021-02-16T19:12:34Z","title":"Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.02683","snapshot_observed_at":"2026-08-10T20:19:48.143474Z","title":"Preventing unauthorized use 15 of proprietary data: Poisoning for secure dataset release","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.143474Z"},"links":{"cited_paper":"/paper/2103.02683","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:8a5f2ce2b88683f51921053aa9ab3d6cc4438d3b0085355dbd65f245a3af2e19","observation_id":"79e9ef43-6270-4a9e-b38f-08e5c8625da8","resolution":{"observed_at":"2026-08-10T20:19:48.143474Z","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":"2026-08-10T20:19:49.059495Z","title":"Adversarial examples make strong poisons","venue":null,"work_id":"26901106-97dd-4b47-b688-80a9710149f2","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.147865Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:f9e291bff831e1161544f0e9f65ac88e39ee266cdb3da0553b608c83db27ddf0","observation_id":"24f2ff96-b04f-451b-8803-ebc69c6af769","resolution":{"observed_at":"2026-08-10T20:19:49.064199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.044365Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures","venue":null,"work_id":"f2ce7d27-6465-4f6c-bf9f-b2feec625bda","year":2015},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.152027Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:e6a6e5828523d724b5520aebc4257575f304ac22f945413ecb9116de26cc53fe","observation_id":"99f9aeb3-65ef-4451-9ebe-bf6a09610074","resolution":{"observed_at":"2026-08-10T20:19:49.049024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.029919Z","title":"Ro- bust unlearnable examples: Protecting data against adversarial learning","venue":null,"work_id":"0fba133a-f00b-44fa-848b-bd7770178ef0","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.157207Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:d1219b8da02c8f1804dea79c8f2739d7931432774eceb3c82470a98e1f2c3af5","observation_id":"47ac0ed5-fe6d-45f6-ab90-fd9a73c9c9cf","resolution":{"observed_at":"2026-08-10T20:19:49.034941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:49.013951Z","title":"An introduction to the california consumer privacy act (ccpa)","venue":null,"work_id":"f9f9e497-8ae4-44f3-81ec-c1a140b8329c","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.161590Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:dd56fb7cc44ec72d22b24b3b5ac440ed9f218af5e350dc33189341923c735f04","observation_id":"f73934e1-e09f-46de-a92f-2dd68914c85c","resolution":{"observed_at":"2026-08-10T20:19:49.019822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.999518Z","title":"Attribute inference attacks in online social networks","venue":null,"work_id":"6a718caf-f584-4c4e-8535-e63679cd2610","year":2018},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.165664Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:fdebf5b9d157775e5d458737aea62256518e9ddf5b545e4b69c9802341020d7a","observation_id":"60ac2bd2-0b2f-4e17-b043-26ca0a38f69d","resolution":{"observed_at":"2026-08-10T20:19:49.004231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.984703Z","title":"Private data inference attacks against cloud: Model, technologies, and research directions","venue":null,"work_id":"177fd34b-a1fa-4a71-a324-1e72fa376349","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.169691Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:b5ea22b97c0328e7ffcff7a5a71eef5d7362c5bdb40d85e9e75e4523de8fe1a2","observation_id":"c8adcb95-26d9-4ff8-9e39-9a2d6ecd9c44","resolution":{"observed_at":"2026-08-10T20:19:48.989722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.969467Z","title":"Netguard: Protecting commercial web apis from model inversion attacks using gan-generated fake samples","venue":null,"work_id":"5d7cdd1e-ebb1-44d2-95f5-f3b99cdde696","year":2023},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.173613Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:78effd971741d0c28ebfac5c290f7d8c08961926b9ce4c9020f9b84d0d7940cc","observation_id":"efea2aac-a1cc-4eeb-bf6e-82b18c53c016","resolution":{"observed_at":"2026-08-10T20:19:48.974513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.953915Z","title":"Faster autoaugment: Learning augmentation strategies using backprop- agation","venue":null,"work_id":"44d8c21d-5f47-4ed1-a936-8465becb4548","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.177825Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:52a2eb94eece53793c463fccc18bb10fef86604fa1c5a1504140856fbd73d02e","observation_id":"81292e3a-fa8c-4743-9129-daadbdf5319e","resolution":{"observed_at":"2026-08-10T20:19:48.959539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.939005Z","title":"Protecting facial privacy: generating ad- versarial identity masks via style-robust makeup transfer","venue":null,"work_id":"666aff36-b85a-4284-affe-17b03a8b5fc9","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.182138Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:2bc30464a4b16a6e38e55cac284188e0024c26002cce8308d5a2a51d8fa16b74","observation_id":"69f702fb-0f54-4c26-ad05-8174b1441308","resolution":{"observed_at":"2026-08-10T20:19:48.943691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.923507Z","title":"Unlearnable examples: Making personal data un- exploitable","venue":null,"work_id":"adcb93db-cbde-4295-8d97-c5566f2009f9","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.186811Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:d3a6ecd631df96c5bd4b3b812a8a11c3e67f455ef7ec0c5f3db077de05ddea08","observation_id":"fc8b24d6-7c75-45f1-afd1-67eca6b75ffe","resolution":{"observed_at":"2026-08-10T20:19:48.928956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.908195Z","title":"Fast adversarial training with adaptive step size, 2022","venue":null,"work_id":"7bc4599e-9e30-4ee0-add8-012924591ee9","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.191479Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:ead75646c9f58b3625bbe7796a62dad028776123b2179f0a33a297535172eddd","observation_id":"694dbff5-b467-40be-af7a-533e038e1d46","resolution":{"observed_at":"2026-08-10T20:19:48.913461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.892354Z","title":"Puzzle mix: Ex- ploiting saliency and local statistics for optimal mixup","venue":null,"work_id":"4f3b51a2-bd8e-44d8-b0a9-187be18d2e31","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.195711Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:9152b74ab536b77a2bd5235ef73ec6aae95258e57281e8bd812a914ff3fa15e6","observation_id":"b2007f30-265f-4875-87c5-a83078efeed3","resolution":{"observed_at":"2026-08-10T20:19:48.898129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.877497Z","title":"Swift: Super-fast and robust privacy-preserving machine learning","venue":null,"work_id":"6f2cecda-4522-4f68-9c7f-0e2a87fe12af","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.200806Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:06607739229b7c24a737cf1fe5823e8231dec9725ddb88b745dfee280e6757ad","observation_id":"10705842-d156-4d44-931d-b52874b0ca80","resolution":{"observed_at":"2026-08-10T20:19:48.882329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.205164Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.205164Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:f6adc1e66267aa69aec5ac939df9789dce393c652b8b148df39858a164e1ff50","observation_id":"4ef8ad1d-9e14-49d1-92d1-9ad43eba6d9b","resolution":{"observed_at":"2026-08-10T20:19:48.205164Z","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":"2026-08-10T20:19:48.853043Z","title":"Adversarial machine learning at scale","venue":null,"work_id":"562bf614-4640-47bd-bfff-ec3d9b90ddc1","year":2017},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.209577Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:e0dbc6d3c9c43aca241c1ec18db2c07900b21623e56382640c2e9d04ca75ad6f","observation_id":"61edf612-6918-4256-935b-175a1e2bd3a4","resolution":{"observed_at":"2026-08-10T20:19:48.858109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.836829Z","title":"Fast autoaugment","venue":null,"work_id":"f92e54fd-535d-44ab-a19e-d87b4bdacbdb","year":2019},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.213745Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:a62c1d1284136581b442b48180011de2cfe6442dfa3c77ff3bd0ceb2dc8857bd","observation_id":"fd3141e7-2322-4466-b92c-1c677aa353e8","resolution":{"observed_at":"2026-08-10T20:19:48.841536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13244","last_updated":"2021-11-25T20:32:15Z","snapshot_observed_at":"2026-07-06T12:12:18.828330Z","submitted_at":"2021-11-25T20:32:15Z","title":"Going Grayscale: The Road to Understanding and Improving Unlearnable Examples","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13244","snapshot_observed_at":"2026-08-10T20:19:48.218407Z","title":"Going grayscale: The road to understanding and improving unlearnable examples","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.218407Z"},"links":{"cited_paper":"/paper/2111.13244","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:04be5867b68880845552c794477d114bd080edf8c6e7c24d2689f1217b33505d","observation_id":"80974c03-5e05-4ea4-9790-f803b373f03f","resolution":{"observed_at":"2026-08-10T20:19:48.218407Z","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":"2026-08-10T20:19:48.822475Z","title":"Feature distillation: DNN-oriented JPEG compression against adversarial examples","venue":null,"work_id":"ccc0344d-83b6-4ffd-a8c2-cb8fd68ffab9","year":2019},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.223736Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:72f39359a4695472de8be23999dc4f6f742effcdefdd33b4a1d88dfa068c1730","observation_id":"3008ff65-dee5-417b-9452-4de890230846","resolution":{"observed_at":"2026-08-10T20:19:48.827281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.808639Z","title":"Discriminator-free generative adversarial attack","venue":null,"work_id":"6f6e0d12-4743-4b8e-88ed-f7e8135ab698","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.228765Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:09c53e910190efe566c72db252b0c240efd25da0895f034e42abda4c6e10e68b","observation_id":"9aeb6e22-5854-4bb9-9131-65a6518ac0df","resolution":{"observed_at":"2026-08-10T20:19:48.813164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.795599Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"8563191c-a295-4fbf-a093-42b1349a9787","year":2018},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.233454Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:84d83111956ee35da4228f259c555d2b0a1796eeebb87cbc292b45f73fe03c53","observation_id":"2bdafffa-068f-472a-8f10-2a6c3616da17","resolution":{"observed_at":"2026-08-10T20:19:48.799997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.781343Z","title":"A review: Data pre-processing and data augmentation techniques","venue":null,"work_id":"3839a20f-2e7e-47b5-b07c-367cc48eab97","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.238561Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:618f6754fe152664156aeea04bcda0a173a535f9d2ad9aa9cb500fa8e68db468","observation_id":"65e0b70e-a8d6-47be-93a8-1993e0f6da35","resolution":{"observed_at":"2026-08-10T20:19:48.785783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.767986Z","title":"Deep learning applications and challenges in big data analytics","venue":null,"work_id":"a668b96b-b750-4cbd-8088-5046519ed672","year":2015},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.243147Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:6bb0de9120204e739d763ce902d19a2964fc7c1b76c2c50c153029b270402eb7","observation_id":"5ec9f769-7d6b-4a2a-89b1-27fd07d03638","resolution":{"observed_at":"2026-08-10T20:19:48.772399Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.753405Z","title":"Deep face recognition","venue":null,"work_id":"ae643d28-7daa-4e43-a8a9-202cb888e811","year":2015},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.247653Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:52238d28abf68d443d8972552885e128cf659adc18e89fafbe46cfd1b93653d4","observation_id":"49b2aff9-e5f7-4991-89b4-3cc275255d5f","resolution":{"observed_at":"2026-08-10T20:19:48.758214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.739053Z","title":"Deepsweep: An evaluation framework for mitigating dnn backdoor attacks using data augmentation","venue":null,"work_id":"5977b060-d25d-4925-86a4-8cd2a9518c48","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.252188Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:4c9e300ae52eb68fde19880ed8b021c7f35e5e64992ea6e2cf5dd5562a5053bf","observation_id":"0024e676-2c3d-49f5-bbaa-25c483948691","resolution":{"observed_at":"2026-08-10T20:19:48.743735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.01701","last_updated":"2020-12-03T04:56:06Z","snapshot_observed_at":"2026-07-06T10:20:13.545492Z","submitted_at":"2020-12-03T04:56:06Z","title":"FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.01701","snapshot_observed_at":"2026-08-10T20:19:48.256789Z","title":"Fencebox: A platform for defeating adversarial examples with data augmentation techniques","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.256789Z"},"links":{"cited_paper":"/paper/2012.01701","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:32e9101fca0e645d046a77dab5d76a31dad86649934fc0630aa9ba4a64cc6d58","observation_id":"c4d1d38c-37ea-4ce4-b686-aca0af236604","resolution":{"observed_at":"2026-08-10T20:19:48.256789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.14851","last_updated":"2022-03-14T09:56:26Z","snapshot_observed_at":"2026-07-06T11:23:53.571225Z","submitted_at":"2021-06-28T17:06:19Z","title":"Data Poisoning Won't Save You From Facial Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.14851","snapshot_observed_at":"2026-08-10T20:19:48.263072Z","title":"Data poisoning won’t save you from facial recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.263072Z"},"links":{"cited_paper":"/paper/2106.14851","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:946fc0ed32b2dfaad37836a4f439840b351f84e77f5998de6a8386932b396bee","observation_id":"c30a777e-c56c-40dc-8c08-0dc10bcd7306","resolution":{"observed_at":"2026-08-10T20:19:48.263072Z","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":"2026-08-10T20:19:48.724923Z","title":"Data augmentation can improve robustness","venue":null,"work_id":"4e2f8c68-d980-4961-8b15-0d130a7f0810","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.269297Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:3042a14ed0d07316e70c758606b350503929d26f8fd9a9af488bd2608620237a","observation_id":"c7c59ca6-dc92-43a4-ae4a-ab840344889e","resolution":{"observed_at":"2026-08-10T20:19:48.729543Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.711076Z","title":"Transferable unlearnable examples, 2022","venue":null,"work_id":"1f601f2e-659e-4b43-946b-6506a3a2cbaf","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.274326Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:0ececf6b083bb03e416e9a80e9e4ae377cda1afe14f81ff6d3d8219023275d8c","observation_id":"33bcdbd0-be7e-4456-bfa2-734ea695b008","resolution":{"observed_at":"2026-08-10T20:19:48.715539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.697052Z","title":"Fawkes: Protecting privacy against unauthorized deep learning models","venue":null,"work_id":"4bcd93f7-7cf1-46f9-af47-ec8a4f08e1d8","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.278701Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:67ac93ca0d445d83a01b3fd48aa71dab376688898ab7fad7f520cb6b799a0d03","observation_id":"70878829-5d5e-4243-9ad1-7c682996e431","resolution":{"observed_at":"2026-08-10T20:19:48.701767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.682923Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"a1e63aa0-902a-4bc5-be74-32881f5750f3","year":2017},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.282958Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:4fa82fd9efcce6f4473019aa6baae241e898ea46611883c2ddb9d850461dac96","observation_id":"b38396c3-4006-4132-81bb-b53dba975bef","resolution":{"observed_at":"2026-08-10T20:19:48.687693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.287598Z","title":"Smith and Nicholay Topin","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.287598Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:0e27efb5a6d2286f2d4a34c51f34ecd34bb1ad09be584773bbb76c2e1d07eea0","observation_id":"c6a73052-4a6c-4c57-92dc-85ce5e0359f0","resolution":{"observed_at":"2026-08-10T20:19:48.287598Z","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":"2026-08-10T20:19:48.658674Z","title":"Revisiting unreasonable effectiveness of data in deep learning era","venue":null,"work_id":"e4d1710e-77ac-42bc-b1e5-e3aad110370f","year":2017},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.293058Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:dc3b6ce171be41aba45ca776a71f1a4ede2320e627d63b6efec586552e853812","observation_id":"b0db3930-2a2a-4a77-ab33-2ef68ea87a33","resolution":{"observed_at":"2026-08-10T20:19:48.663273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.644345Z","title":"Mitigating membership inference attacks by self-distillation through a novel ensemble architec- ture","venue":null,"work_id":"a4882777-47fa-441d-ac4c-0083c7daa00d","year":2022},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.297991Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:0a6bf594f9e8041475f8eeaf7fe09da138b7f6a2483f809649480f5cf9e3062f","observation_id":"aaf612c3-b295-4580-adf6-9335d10f0166","resolution":{"observed_at":"2026-08-10T20:19:48.648994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.631678Z","title":"The calculation of posterior distributions by data augmentation","venue":null,"work_id":"39778123-96b7-459e-9a4b-f1d1d39b183c","year":1987},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.302550Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:2c5278099c3d9bb3ad02cf3c7eafaad506a33d284edc8eebc4d677f5b21e753b","observation_id":"dfa0012f-dba6-487e-9801-55c93450156a","resolution":{"observed_at":"2026-08-10T20:19:48.635933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.618089Z","title":"The art of data augmentation","venue":null,"work_id":"79a5e9cd-008e-4ef2-bcd9-96361a4e32a7","year":2001},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.307444Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:ee95757125610d3661cb797041ef122d0cb0ca593dd2f5e1e97a199158211c84","observation_id":"c7110f71-6f37-4737-a155-252909b9e3e4","resolution":{"observed_at":"2026-08-10T20:19:48.622812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.604327Z","title":"The eu general data protection regulation (gdpr)","venue":null,"work_id":"238628bc-3b24-4280-b7f7-e6fdc5ad94b1","year":2017},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.312247Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:3503d1edb957714b8304f8564f7c68bc2034c1f11607af547adf0e80ffd0a726","observation_id":"ccf7dac2-9cfe-4f6c-8a02-121746f95376","resolution":{"observed_at":"2026-08-10T20:19:48.609018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.590364Z","title":"The JPEG still picture compression standard","venue":null,"work_id":"bb43fbb4-4780-46c9-b66f-df3829dc3e5b","year":1992},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.316219Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:849660c199af59235041f67fb649878083ba24ca672f6d27a5b9e34009e27d16","observation_id":"99a190fe-947e-4398-9af2-0cfebd240958","resolution":{"observed_at":"2026-08-10T20:19:48.595555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.574453Z","title":"Non- local neural networks","venue":null,"work_id":"02d2b79f-e512-43dd-9d0d-a08ee4b2752a","year":2018},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.320539Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:22639ca8d033a19611688a4f028b317b952e31006a12d4438cce0d3fcf9cd819","observation_id":"0b70d6ce-faaf-4b5c-9c49-868f1b1b57d3","resolution":{"observed_at":"2026-08-10T20:19:48.579957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.558304Z","title":"Recent advances in deep learning","venue":null,"work_id":"dce520e0-674e-41da-aed6-4a376d1c2e78","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.324703Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:028f729fa4827390bfdfe4ae11098dc1025662d0de5ac3e6cdf062c4f1346be0","observation_id":"e5a8282f-3d24-409c-b9c2-90b5a9bb6750","resolution":{"observed_at":"2026-08-10T20:19:48.563549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.542328Z","title":"Patchguard: A provably robust defense against adversarial patches via small receptive fields and masking","venue":null,"work_id":"4b5637aa-328b-4cc8-836c-31ca0ea095bf","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.329544Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:ff64fb871fd4245e69ee757c4f45e706f11d0d2f2688e65233054ef906c8944a","observation_id":"340625db-e9fd-44e2-b755-e43a310c2eb8","resolution":{"observed_at":"2026-08-10T20:19:48.546958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.527151Z","title":"Neural tangent generalization attacks","venue":null,"work_id":"8994f146-a937-4bff-a178-fbd633d5dcaa","year":2021},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.334327Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:7878f221770f827274a703d83f65fcf3fe37da65fd8504070a7384475ed5f850","observation_id":"80b8ba37-6eca-4a37-951f-a8a26ea4837c","resolution":{"observed_at":"2026-08-10T20:19:48.532425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.512561Z","title":"A data augmentation-based defense method against adversarial attacks in neural networks","venue":null,"work_id":"922bb096-2ca7-4d9f-8755-7fad6627d486","year":2020},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.339440Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:15665785f978b5a16afbefb85dd8693eec28e9a361c44066fa6cab045968609b","observation_id":"bd9325d7-3b4d-4287-a410-d25f243ac8a6","resolution":{"observed_at":"2026-08-10T20:19:48.517639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-10T20:19:48.495580Z","title":"You only propagate once: Accelerating adversarial training via maximal principle, 2019","venue":null,"work_id":"b510b2e3-4a1c-4509-97b5-6013af10644d","year":2019},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.344232Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:44ab411a7506dcf3276dc4eac4d41a07a9abcf05cb63ad65b1972a4b941ed7c2","observation_id":"bfd4e891-087d-4362-8668-8b58b453fa24","resolution":{"observed_at":"2026-08-10T20:19:48.501314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.09412","last_updated":"2018-04-27T21:39:25Z","snapshot_observed_at":"2026-08-08T10:28:19.597631Z","submitted_at":"2017-10-25T18:30:49Z","title":"mixup: Beyond Empirical Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.09412","snapshot_observed_at":"2026-08-10T20:19:48.348732Z","title":"mixup: Beyond empirical risk minimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.348732Z"},"links":{"cited_paper":"/paper/1710.09412","citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:3ed59f5a529f4b526401d3b2fbe2108613fb16eb1906d84221fee9fbb32c0a44","observation_id":"ec069a34-88ca-480c-8128-86d95a2ace35","resolution":{"observed_at":"2026-08-10T20:19:48.348732Z","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":"2026-08-10T20:19:48.478658Z","title":"Top Minds","venue":null,"work_id":"29fbefa0-4456-40b6-a587-38e36ce46b45","year":2023},"citing_paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T20:19:48.353611Z"},"links":{"citing_paper":"/paper/2501.08862"},"observation_digest":"sha256:7ab9d694bc9e815dbc629e2de29ebf710041f1b3657bf5f36aa1b366ba8d63c5","observation_id":"330cdf9c-4188-4657-924f-06fb478acc03","resolution":{"observed_at":"2026-08-10T20:19:48.484588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.08862","last_updated":"2025-01-15T15:22:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T20:13:38.417903Z","submitted_at":"2025-01-15T15:22:57Z","title":"ARMOR: Shielding Unlearnable Examples against Data Augmentation"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":46},"total_outbound_references":54},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 3 inbound Pith citation observations for arXiv:2501.08862."}