{"as_of":"2026-08-16T14:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:53d0e653799247d47ed764ab2aa6112edab8fabc3edd881ed1ecc1ef1160d05d","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:28:27.864049Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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":"2026-08-11T20:28:26.773061Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-11T20:28:28.020622Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"cited_work":{"arxiv_id":"2412.05767","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.05767","snapshot_observed_at":"2026-08-11T20:28:28.020622Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","venue":"cs.LG","work_id":"23e2653e-0ed9-4022-86bc-637c4e3a4d7b","year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.773061Z"},"links":{"cited_paper":"/paper/2412.05767","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:307a21a607395cd042efe10bd57452be6ca8f1dffc6430d508f34371c11ee0fb","observation_id":"9694ba5b-b17e-4218-b27a-197ab668995d","resolution":{"observed_at":"2026-08-11T20:28:28.027288Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.05767/citation-record","integrity":"/paper/2412.05767/integrity","json":"/paper/2412.05767/citation-record.json","paper":"/paper/2412.05767"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"cited_work":{"arxiv_id":"2412.05767","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.05767","snapshot_observed_at":"2026-08-11T20:28:28.020622Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","venue":"cs.LG","work_id":"23e2653e-0ed9-4022-86bc-637c4e3a4d7b","year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.773061Z"},"links":{"cited_paper":"/paper/2412.05767","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:307a21a607395cd042efe10bd57452be6ca8f1dffc6430d508f34371c11ee0fb","observation_id":"9694ba5b-b17e-4218-b27a-197ab668995d","resolution":{"observed_at":"2026-08-11T20:28:28.027288Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:29.152143Z","title":null,"venue":null,"work_id":"33f31916-9089-4d6c-b687-24a2a7fe8145","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.781691Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:549ed0f2868a0ab59c201dd6ee209cdaae345ddfe727ebd2e4ac5ad71f59d4a7","observation_id":"56f169a6-d1b7-485a-9396-27919a64da0a","resolution":{"observed_at":"2026-08-11T20:28:29.183136Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:29.007721Z","title":null,"venue":null,"work_id":"ce580ed3-6a83-43e8-9e67-93b0ba94b2f6","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.838861Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:1e953d570cb72f5724c08b5a70e15af1b19cde6130985371bdf622f254cc17bd","observation_id":"476ea691-b9a5-4586-90ed-3e0b4accc600","resolution":{"observed_at":"2026-08-11T20:28:29.072331Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.978447Z","title":"DeMem can be seamlessly integrated into various adver- sarial training techniques","venue":null,"work_id":"78939bca-d0e8-4dea-a013-49fe1ebc7e67","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.895993Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:56e4429dd39fad67b1d0fdaae6f5121e32b360dc83e0e3465f0f81e6e05a393e","observation_id":"2eb701e4-1c27-460c-b46d-dfde38b778ea","resolution":{"observed_at":"2026-08-11T20:28:28.984444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.963379Z","title":null,"venue":null,"work_id":"50f777dc-2df8-462b-b7c9-d903c1540bb4","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.946974Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:2fb05af1781c293ffa137c8d34a599483339960bee513404b1fc04d64988de7a","observation_id":"b20045a9-bdcb-4b44-af2f-ede856beff11","resolution":{"observed_at":"2026-08-11T20:28:28.967895Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.947706Z","title":"We then analyze individual samples to explain why DP can fail, followed by a detailed presentation of our proposed approach","venue":null,"work_id":"7cba61e1-585f-47ce-a8c0-0079aed37150","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.951707Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:b4cbbcc67e30b25e9f3247354dba2cdefb10c4f88c7438f865c436e6599549ef","observation_id":"1f418cd8-787f-4162-9e5d-5714cfffc013","resolution":{"observed_at":"2026-08-11T20:28:28.952275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.932993Z","title":"Setup Experiments were conducted on 8 NVIDIA 4090 GPUs using PyTorch [27]","venue":null,"work_id":"caf14862-ac16-4a18-8457-f5eaf77732cf","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:26.999216Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:8fcbadf7112c45d9a2e4ab4df133483ae0c1e1206fc711ce92459a659e74ccee","observation_id":"f1919fcf-24e2-4087-8322-933855285a80","resolution":{"observed_at":"2026-08-11T20:28:28.937611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.918487Z","title":null,"venue":null,"work_id":"5b640f0d-ffdc-4c86-8c00-4c8a62a710ab","year":null},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.162592Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:40a754a0627d329f97d8ddb3e55bbb865a3893032480c6447d1a9331868d544d","observation_id":"fe71f7b8-0018-4d1d-bef9-9cddf7f54da3","resolution":{"observed_at":"2026-08-11T20:28:28.923474Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.903656Z","title":"An adversar- ial perspective on accuracy, robustness, fairness, and privacy: Multilateral-tradeoffs in trustworthy ml,","venue":null,"work_id":"1a2d38f7-7b8d-4733-b1e0-bc4c04bc2dec","year":2022},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.211088Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:f814560f8c221c67c4eac9c33490b9024ffd7713156d805721a747deae69bc6b","observation_id":"5da869c3-28a6-43c9-8c70-ce4d0942f23f","resolution":{"observed_at":"2026-08-11T20:28:28.908411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.888807Z","title":"On the privacy risks of algorithmic fairness,","venue":null,"work_id":"87c34718-5943-4a65-9ad3-b1af060b09d6","year":2021},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.225809Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:adb8701cca4cad7b27d1b739dc818ee4d0f65199ee77979dc12b6c1ec77ea5b5","observation_id":"860e5ab9-7c9a-49f4-9288-ba29187ad096","resolution":{"observed_at":"2026-08-11T20:28:28.893575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00315","last_updated":"2025-03-19T05:26:47Z","snapshot_observed_at":"2026-08-16T13:29:20.149054Z","submitted_at":"2024-08-01T06:26:05Z","title":"ADBM: Adversarial diffusion bridge model for reliable adversarial purification","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00315","snapshot_observed_at":"2026-08-11T20:28:27.295060Z","title":"Adbm: Adversar- ial diffusion bridge model for reliable adversarial purification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.295060Z"},"links":{"cited_paper":"/paper/2408.00315","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:6573399134b08bfcfec6db264505477ed7eade262be58882a5cfac6cc95568b1","observation_id":"dd726b66-94be-46d3-a7ba-b5030f7307a6","resolution":{"observed_at":"2026-08-11T20:28:27.295060Z","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":"2026-08-11T20:28:28.849429Z","title":"Language-driven anchors for zero-shot adver- sarial robustness,","venue":null,"work_id":"983a5807-e12c-4e20-88e1-23f0ab2244a2","year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.300118Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:90467f6c2163c4162c6319de7595d5f8c10e155a962a46fb7dc5ac8a4287978c","observation_id":"c4becd87-6d9c-491e-a82d-ca19f3b0112b","resolution":{"observed_at":"2026-08-11T20:28:28.878189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.15362","last_updated":"2026-05-19T04:19:17Z","snapshot_observed_at":"2026-08-16T12:15:08.381172Z","submitted_at":"2024-10-20T11:27:41Z","title":"Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.15362","snapshot_observed_at":"2026-08-11T20:28:27.305592Z","title":"Faster-gcg: Efficient discrete optimization jailbreak attacks against aligned large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.305592Z"},"links":{"cited_paper":"/paper/2410.15362","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:a896c646896bfbe1d5afde3abcfd481a2ce956f0f613783d0a2e7697c63cc585","observation_id":"7e124fb9-c07a-4460-ac9c-abc8edb50dd7","resolution":{"observed_at":"2026-08-11T20:28:27.305592Z","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":"2026-08-11T20:28:28.655036Z","title":"Privacy risks of securing machine learning models against adversarial exam- ples,","venue":null,"work_id":"8da35bc2-d359-4f86-8b29-f0e2042b7257","year":2019},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.311835Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:e294179bf2c0e5fc0223b1dea2811e50d04a067c4ebc6b2b10061b4f84ce904e","observation_id":"1b6644c5-e48d-4037-a2ea-2b73d459274c","resolution":{"observed_at":"2026-08-11T20:28:28.743082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.641155Z","title":"On the privacy effect of data enhancement via the lens of memoriza- tion,","venue":null,"work_id":"42115506-d3df-4f48-ba0e-da55310f5837","year":2024},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.316122Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:0a38b5a4ebd0eb37f481f4238ad73f23724481845afc3fcbb60681ca74cf2623","observation_id":"49167c93-1b49-4279-968c-d533da13cd33","resolution":{"observed_at":"2026-08-11T20:28:28.645782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.626627Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":"40b0ca11-c62f-42b1-9d9b-1a65c244947d","year":2017},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.343311Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:1a6b8594e83c87f5eb20e5aa635c2207a8e8e73a23cc3973ffe66b804333af2a","observation_id":"6e761f78-c522-4019-8a07-9e3b58a3c55d","resolution":{"observed_at":"2026-08-11T20:28:28.631643Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.07828","last_updated":"2021-08-25T09:42:30Z","snapshot_observed_at":"2026-07-06T10:24:22.088463Z","submitted_at":"2020-12-14T18:59:24Z","title":"Robustness Threats of Differential Privacy","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.07828","snapshot_observed_at":"2026-08-11T20:28:27.349811Z","title":"Robustness threats of differential privacy,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.349811Z"},"links":{"cited_paper":"/paper/2012.07828","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:b8ec33ca24f294d37d362fa9eed8790dc141beff6cf786ddbbe26246c70be807","observation_id":"c7623a50-6641-474d-8ba9-0a136ebabad3","resolution":{"observed_at":"2026-08-11T20:28:27.349811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.02265","last_updated":"2022-01-06T22:33:06Z","snapshot_observed_at":"2026-08-15T10:02:23.097619Z","submitted_at":"2022-01-06T22:33:06Z","title":"Learning to be adversarially robust and differentially private","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.02265","snapshot_observed_at":"2026-08-11T20:28:27.355483Z","title":"Learning to be adversarially robust and differentially private,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.355483Z"},"links":{"cited_paper":"/paper/2201.02265","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:ad14ecc38736d7d53383fcfe1e89fdf041881d39c3aa45c3d1ff9c314a545797","observation_id":"0e7f07a2-8904-4ddc-9cd6-e90065e347ac","resolution":{"observed_at":"2026-08-11T20:28:27.355483Z","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":"2026-08-11T20:28:28.611350Z","title":"Deep learn- ing with differential privacy,","venue":null,"work_id":"8ca513b2-9d78-47b2-b86d-4d79d20588fd","year":2016},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.362720Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:a6d51d08865588c1e20a83effcc664b93c0f9ca612d18cbd5849e3608394b0f4","observation_id":"06637edf-cbf4-467d-b3fd-3d6f374684ba","resolution":{"observed_at":"2026-08-11T20:28:28.617182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.597400Z","title":"Does learning require memorization? a short tale about a long tail,","venue":null,"work_id":"721948e0-a32b-413e-be7c-af26d4f458fe","year":2020},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.386133Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:ea030c289396f5d8eb6ab0d5cef6ebe11a0999f4a9098cc2f78d44ce84eb1abd","observation_id":"a300d9e6-3d1f-4004-abeb-faec7dcdaf28","resolution":{"observed_at":"2026-08-11T20:28:28.601673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.580000Z","title":"What neural networks memorize and why: Discovering the long tail via influence es- timation,","venue":null,"work_id":"b15d76e0-b19a-4b4a-852a-921c1a749c3b","year":2020},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.391008Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:73c2ba5480a68bccb6d8d66941ae8dc2ad38cd26c5f303fb8f6eb26a3ad79436","observation_id":"bf4f2abc-8368-442f-850e-943eab575a70","resolution":{"observed_at":"2026-08-11T20:28:28.585849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-11T20:28:27.395884Z","title":"Towards deep learn- ing models resistant to adversarial attacks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.395884Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:a12b1519c2ca6f724d175701362b43aee74dc1913e06ec30eba1bbe19f4294f8","observation_id":"735d1115-6be5-42fd-95a7-afefe2f04d8b","resolution":{"observed_at":"2026-08-11T20:28:27.395884Z","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":"2026-08-11T20:28:28.565587Z","title":"Theoretically principled trade-off between robustness and accuracy,","venue":null,"work_id":"241739dc-ccb4-4604-a6dd-ef4bc98b0839","year":2019},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.407755Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:62f122643aed48bac88e1d8a2651ddd1f547ae30de02ff3036101fb9092622ac","observation_id":"d78529ef-5011-42bf-a2e0-89e60d6e4fdb","resolution":{"observed_at":"2026-08-11T20:28:28.569902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-11T20:28:27.413085Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.413085Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:45c8f74ee8ea7886a4ac05c22c9e851e1da3b31cbbd4fb2e476a0424a70e42ea","observation_id":"cea19936-b30f-4506-9d7b-bd297b20d286","resolution":{"observed_at":"2026-08-11T20:28:27.413085Z","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":"2026-08-11T20:28:28.549877Z","title":"Robust physical-world attacks on deep learning visual classification,","venue":null,"work_id":"cbfb1889-f517-41a0-a791-b3afe1f9c02a","year":2018},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.424817Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:3cd08cbed262952b94f85ee62af077472bbe65a724f759c555383e4ba2fd3c9a","observation_id":"a54201c0-009f-4614-b3cb-e3f401ede91c","resolution":{"observed_at":"2026-08-11T20:28:28.555173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.533172Z","title":"Adversarial weight perturbation helps robust generalization,","venue":null,"work_id":"47e03e70-ddf0-4d31-aa50-1d21329776a0","year":2020},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.429649Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:bb9d392126eb2a6cc96b82f59c84cc61bba6bc0dfc9593e1361d609a447ce663","observation_id":"d86f0e1e-25a6-426a-8169-272760189133","resolution":{"observed_at":"2026-08-11T20:28:28.538232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.482049Z","title":"Differential privacy,","venue":null,"work_id":"77eccb63-74d5-4f31-bc07-1d8bcdd98bc7","year":2006},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.438903Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:daaa8bef1568556a210420a292f1f36b76cc75596bfeaa37e8e2e56ffa095c96","observation_id":"d51a13b8-fefe-4973-a5d5-864b1b5bf4bf","resolution":{"observed_at":"2026-08-11T20:28:28.523629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.266216Z","title":"Quality control of voice recordings in re- mote parkinson’s disease monitoring using the infinite hidden markov model,","venue":null,"work_id":"517daf89-4f2a-446c-85b4-1cc361cb0ef4","year":2019},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.443546Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:22161744fa2d405d3c08ecd344354cf20844063b54d43f53c9fd89bb51ff12a5","observation_id":"5d743e88-1458-4b95-b327-2e9a22a140e7","resolution":{"observed_at":"2026-08-11T20:28:28.351377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.129759Z","title":"Membership inference at- tacks from first principles,","venue":null,"work_id":"6fe75b0d-b373-4cc4-842c-561844f8e20c","year":2022},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.457899Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:2bf58112515b38a3489ce457b9aa0607841ece1f03a7d759f623553e1c4e8f0c","observation_id":"fdc896c1-501f-4c11-8666-1801eef60dd0","resolution":{"observed_at":"2026-08-11T20:28:28.173052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01246","last_updated":"2018-12-14T19:39:43Z","snapshot_observed_at":"2026-08-16T13:40:06.467812Z","submitted_at":"2018-06-04T17:38:42Z","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.01246","snapshot_observed_at":"2026-08-11T20:28:27.463491Z","title":"Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.463491Z"},"links":{"cited_paper":"/paper/1806.01246","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:6154d9a33dc026da0e0474937c87913bfc260f4621b7a9485bae0a07bfea06ef","observation_id":"816b3943-1e7b-4a4e-8726-d325496a7c54","resolution":{"observed_at":"2026-08-11T20:28:27.463491Z","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":"2026-08-11T20:28:28.115104Z","title":"Privacy risk in machine learning: Analyzing the con- nection to overfitting,","venue":null,"work_id":"2de93642-deb6-42a6-a56c-d7714476706f","year":2018},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.513614Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:fb8463240616232302465cdd895f302922b7dd66be389d9cbdc14e50053f0b3c","observation_id":"3ecb4307-dae7-4b8f-af7d-54b9bdb62601","resolution":{"observed_at":"2026-08-11T20:28:28.119932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.099229Z","title":"Systematic evaluation of pri- vacy risks of machine learning models,","venue":null,"work_id":"7787bd8e-9a1a-4f59-ad01-ec00fe8328e5","year":2021},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.630743Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:7043bad7206a3451ff07010f27d9b78d9ea7f799985eed6f1567315ca3ea7a9a","observation_id":"a16c81e9-5c27-4943-9bd4-4db28915e47d","resolution":{"observed_at":"2026-08-11T20:28:28.104941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.083807Z","title":"On the difficulty of membership inference attacks,","venue":null,"work_id":"e799f751-22ea-48f0-b335-a012a43b883b","year":2021},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.684313Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:1b87022ebcfd077c065cb7a7ac89fbca7aa56fa1f01a3d15ca0eabf118ac4dac","observation_id":"0fd258ca-86bf-4aac-a3db-d2b238c31571","resolution":{"observed_at":"2026-08-11T20:28:28.088374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.069211Z","title":"To trust or not to trust prediction scores for membership in- ference attacks,","venue":null,"work_id":"dc72dc74-3689-4724-8b93-b56f6b31ad5f","year":2022},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.754955Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:7704a91d50ee3d37e6f56511ff17adaa9ac8827026dfc836cd4c1423f9f81177","observation_id":"3eab1dd7-9d0c-4a51-bd5d-86ffd7f3d5de","resolution":{"observed_at":"2026-08-11T20:28:28.074095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.053360Z","title":"Pytorch: An imperative style, high- performance deep learning library,","venue":null,"work_id":"8a2ac5aa-1411-4bbc-90f3-3d8aaa4e7f54","year":2019},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.853952Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:114d3b5ad27bc2ef51fe545c9b61a17af1876410b605fe7dd9b4c66c06abd02b","observation_id":"b78051cb-5f2f-4730-ba80-baf887459c5e","resolution":{"observed_at":"2026-08-11T20:28:28.058385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-11T20:28:28.037843Z","title":"Deep residual learning for image recog- nition,","venue":null,"work_id":"1183815b-1529-4a3d-bf1c-57fdecb53425","year":2016},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.859171Z"},"links":{"citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:2e0226916b62036397726ae86395a51d1e6b955bfdaff12762177f43cc96cd4f","observation_id":"69e6a893-a350-40ac-bda9-22f10eedf74c","resolution":{"observed_at":"2026-08-11T20:28:28.043475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.12298","last_updated":"2022-08-22T20:24:50Z","snapshot_observed_at":"2026-08-13T18:05:03.063224Z","submitted_at":"2021-09-25T07:10:54Z","title":"Opacus: User-Friendly Differential Privacy Library in PyTorch","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.12298","snapshot_observed_at":"2026-08-11T20:28:27.864049Z","title":"Opacus: User-friendly differential privacy library in pytorch,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T20:28:27.864049Z"},"links":{"cited_paper":"/paper/2109.12298","citing_paper":"/paper/2412.05767"},"observation_digest":"sha256:d48d21ad5961de2499c6c5544b427cbfa66d8bba1eb4749312b835072cf5ab7f","observation_id":"de82fb05-d003-4431-b3e6-51b46b5dabea","resolution":{"observed_at":"2026-08-11T20:28:27.864049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.05767","last_updated":"2025-08-22T21:06:17Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T12:15:54.961742Z","submitted_at":"2024-12-08T00:22:58Z","title":"DeMem: Privacy-Enhanced Robust Adversarial Learning via De-Memorization"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":24},"total_outbound_references":37},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2412.05767."}