{"as_of":"2026-08-14T17:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:973db524be7bd4ccc2d8ba785cb955c67d5822a4ef86d35f2eb3161c6ea78211","coverage":[{"denominator":191,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:26:04.786976Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T17:27:29.241219Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-29T17:33:45.392813Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"cited_work":{"arxiv_id":"2411.09776","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.09776","snapshot_observed_at":"2026-06-29T17:33:45.392813Z","title":null,"venue":null,"work_id":"6c7949a9-bf26-4720-b078-a0f6068a2bef","year":2024},"citing_paper":{"arxiv_id":"2605.27148","last_updated":"2026-06-01T21:00:09Z","snapshot_observed_at":"2026-08-13T05:19:19.427805Z","submitted_at":"2026-05-26T15:10:35Z","title":"Landseer: Exploring the Machine Learning Defense Landscape","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T17:27:29.241219Z"},"links":{"cited_paper":"/paper/2411.09776","citing_paper":"/paper/2605.27148"},"observation_digest":"sha256:fb830ec7880ace2f944daed2241b162f60c0769902edd1f898b6085250798b61","observation_id":"e8802b72-f763-4eea-9f4e-5002eed0ca23","resolution":{"observed_at":"2026-06-29T17:33:45.394463Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.09776/citation-record","integrity":"/paper/2411.09776/integrity","json":"/paper/2411.09776/citation-record.json","paper":"/paper/2411.09776"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.400719Z","title":"Papernot et al., `` SoK : Security and privacy in machine learning,'' in EuroS&P, 2018, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.400719Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:9a13fa1987c4c45b298be8882986705c52f04f7604e02e3ffee6ef465dfe3eb1","observation_id":"8ac0c9bb-39a2-41eb-bcda-8ce08252c49a","resolution":{"observed_at":"2026-08-12T20:26:04.400719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.405745Z","title":"Tian et al., ``A comprehensive survey on poisoning attacks and countermeasures in machine learning,'' ACM Computing Surveys, vol","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.405745Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:0c56f23d87a9608e421c78c6d6035ab26a11f6bbe78b57fff61f68b3340f76f4","observation_id":"2f6d0180-7ce6-4c47-8f6e-e5ff63686e8d","resolution":{"observed_at":"2026-08-12T20:26:04.405745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.409811Z","title":"De Cristofaro, ``A critical overview of privacy in machine learning,'' IEEE Security & Privacy, vol","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.409811Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:841e3e3a4e720e1a007cd590ffb71c9ba346be64d6ca0dc62e83f99fa7b89ba7","observation_id":"d11f648c-f831-4941-b50a-e75da34ef031","resolution":{"observed_at":"2026-08-12T20:26:04.409811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.413962Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.413962Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3b40e95321eafd8b75e5e6f333d177426229e05803c20bdf7dd7a54e9210de69","observation_id":"73e397e9-1e21-4a1e-8c53-1f33cd0de461","resolution":{"observed_at":"2026-08-12T20:26:04.413962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.418102Z","title":"Mehrabi et al., ``A survey on bias and fairness in machine learning,'' ACM Computing Surveys, vol","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.418102Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:97e91a9e6396b0b0787557a8efb91dc2c895a5c50c20848400fe3795686ffa64","observation_id":"9a803556-c8b3-4275-8e9b-a1d6b14a1103","resolution":{"observed_at":"2026-08-12T20:26:04.418102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.422118Z","title":"Pessach and E","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.422118Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:76d37228e2a09f30b1e994cafc9a8dbb4d722d0ac7f4ecafd366283be203429c","observation_id":"f6bf0120-0f6c-4e5f-9191-e612f3862e38","resolution":{"observed_at":"2026-08-12T20:26:04.422118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.426496Z","title":"Li et al., `` SoK : Certified robustness for deep neural networks,'' in SP, 2023, pp","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.426496Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:24f3099226202c3c7c6375b80d0db1449c817567286a0bed7613fcefa82bf4d3","observation_id":"aa689f1b-5b2d-44a1-8c3b-1d335c392119","resolution":{"observed_at":"2026-08-12T20:26:04.426496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.430421Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.430421Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:01d83f305ebb814089cfb0a614dd47d6887539b0db8fadad727876d541ecce35","observation_id":"ac8313e2-ad7e-439d-8ff2-65be6ac31092","resolution":{"observed_at":"2026-08-12T20:26:04.430421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.433971Z","title":"Duddu et al., `` SoK : Unintended interactions among machine learning defenses and risks,'' SP, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.433971Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:c60baf316e94e72ec9510a00f1e8bca31cf6725f34e90a9daf823d5cb455fc9b","observation_id":"c5a1838e-f72e-4bb8-857e-cadcb08b3f45","resolution":{"observed_at":"2026-08-12T20:26:04.433971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.439928Z","title":"Szyller and N","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.439928Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:b88388759f18c638690093e5a4f203c48a4482b4aceb62c4739f3b53070a13c8","observation_id":"5af4500e-fdc3-4100-811f-177b46a334af","resolution":{"observed_at":"2026-08-12T20:26:04.439928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.444077Z","title":"Gittens et al., ``An adversarial perspective on accuracy, robustness, fairness, and privacy: Multilateral-tradeoffs in trustworthy ml,'' IEEE Access, vol","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.444077Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:a92dd286b118ebba4c70c7f423be193a2fd5ea36f412105e68fc1333e7ee4eee","observation_id":"e4dc5df9-4e13-4c49-a7cd-1efc263ec7b9","resolution":{"observed_at":"2026-08-12T20:26:04.444077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16851","last_updated":"2023-07-31T17:11:35Z","snapshot_observed_at":"2026-08-13T10:43:51.147477Z","submitted_at":"2023-07-31T17:11:35Z","title":"Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.16851","snapshot_observed_at":"2026-08-12T20:26:04.448225Z","title":"Liu et al., ``Towards trustworthy and aligned machine learning: A data-centric survey with causality perspectives,'' in arXiv:2307.16851, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.448225Z"},"links":{"cited_paper":"/paper/2307.16851","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:59b8fb5a701b26add428b7bfec0cda580d2553a4ca513e814e14fe95d9831d5b","observation_id":"9406c10e-e95b-4b54-8fa9-75cc04cab38e","resolution":{"observed_at":"2026-08-12T20:26:04.448225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.452898Z","title":"Datta, D","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.452898Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:b0c3d02f798a007a0dda92b943eede3b873f22c8114f812c6d1a0e8d24ce3506","observation_id":"18c143ad-d5c4-4c11-95ff-49ba28600d9d","resolution":{"observed_at":"2026-08-12T20:26:04.452898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.457065Z","title":"Alves et al., ``Survey on fairness notions and related tensions,'' in EURO Journal on Decision Processes, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.457065Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:8e9448afa893c985100240de142ea96d9db42e197719d092ed9064c0ede8dd7e","observation_id":"c8f9439d-2545-4a41-92d4-255e14938a59","resolution":{"observed_at":"2026-08-12T20:26:04.457065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.460968Z","title":"Chen et al., ``Privacy and fairness in federated learning: On the perspective of tradeoff,'' ACM Computing Surveys, vol","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.460968Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:6ad6dfdc4a3203fef5ccd6195a10f23e99de1580ec8496d71398c923eae0ad73","observation_id":"cf073b18-b7ed-4521-8e6b-b3044c5dd219","resolution":{"observed_at":"2026-08-12T20:26:04.460968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.465148Z","title":"Fioretto et al., ``Differential privacy and fairness in decisions and learning tasks: A survey,'' in IJCAI, 2022, pp","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.465148Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:756a96fa68a1d5a5305778eade3400791160601b5242d91376e71ddc18d5c5de","observation_id":"b8e8739a-60e3-477a-94d7-43662717ed12","resolution":{"observed_at":"2026-08-12T20:26:04.465148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.469766Z","title":"Noppel and C","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.469766Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:96c57da350de79ad8d07fe5abd6db59e940fffb004c2042e9c348361d5499b55","observation_id":"4e6a6b45-9478-4fc8-af23-1c4856e0016a","resolution":{"observed_at":"2026-08-12T20:26:04.469766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.474408Z","title":"Ferry, U","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.474408Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:11d8b8a3dc0fc6120389deaf8b60d3c14e2a7fab1f203816e91097bd009afdf7","observation_id":"8205630a-cfba-4ab1-9399-082812a52333","resolution":{"observed_at":"2026-08-12T20:26:04.474408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.478403Z","title":"Yaghini et al., ``Learning with impartiality to walk on the pareto frontier of fairness, privacy, and utility,'' in Workshop on Regulatable ML@NeurIPS, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.478403Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:81c6a8650ae5243bbeec9016dbea6809fd178b70fba8ab00ceefcb84ffbc0e9e","observation_id":"b35ef26a-60c0-44bf-9b84-4f6a7fb862e2","resolution":{"observed_at":"2026-08-12T20:26:04.478403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.482193Z","title":"Madry et al., ``Towards deep learning models resistant to adversarial attacks,'' in ICLR, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.482193Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:41e63e7b11a9454c3d23ddfa3453ddbc656a4a42e44bc3eaeab70802587e66fd","observation_id":"5090ef34-418b-4cab-94bf-9d17f126368c","resolution":{"observed_at":"2026-08-12T20:26:04.482193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.485927Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.485927Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:e9c87f5309ba4e87a8a74101eb396b0a6deecd5da0b377c965c2809d64bf4a2c","observation_id":"b86300fc-f0ff-4fe6-a1cb-445337bf97bc","resolution":{"observed_at":"2026-08-12T20:26:04.485927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.490294Z","title":"Zhang et al., ``mixup: Beyond empirical risk minimization,'' in ICLR, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.490294Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:6af4d283bf7c2c2e26ce424a9da4e3c413c909a6d73c9a1dd49b59641975c50c","observation_id":"90b5a623-f3a4-47c5-b120-394c92eed287","resolution":{"observed_at":"2026-08-12T20:26:04.490294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.04552","last_updated":"2017-11-29T14:51:40Z","snapshot_observed_at":"2026-08-13T11:54:46.030796Z","submitted_at":"2017-08-15T15:21:53Z","title":"Improved Regularization of Convolutional Neural Networks with Cutout","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.04552","snapshot_observed_at":"2026-08-12T20:26:04.494368Z","title":"DeVries and G","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.494368Z"},"links":{"cited_paper":"/paper/1708.04552","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:2d8829e06e3d792cabf898d5044cd4cdcd64a553442ecc5b98705739577ef2fa","observation_id":"261bad12-dab7-4b84-a03a-35de4f190b27","resolution":{"observed_at":"2026-08-12T20:26:04.494368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.498906Z","title":"Rebuffi et al., ``Data augmentation can improve robustness,'' in NeurIPS, 2021, pp","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.498906Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:4beb4a746769aee49cf229df3ae74b4a2f45c70039e5715d41d626191e90a6d6","observation_id":"72cbcc8c-545a-454b-be2a-897f167980dc","resolution":{"observed_at":"2026-08-12T20:26:04.498906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.503006Z","title":"Zhang et al., ``Theoretically principled trade-off between robustness and accuracy,'' in ICML, 2019, pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.503006Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:d926e90ab8631ffc31c1bf62599bcceefc360f50ea0a86b70934a2e952892d9c","observation_id":"fc2d4877-2076-4bd2-babc-24c760a64197","resolution":{"observed_at":"2026-08-12T20:26:04.503006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.507147Z","title":"Cohen et al., ``Certified adversarial robustness via randomized smoothing,'' in ICML, 2019, pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.507147Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:245b3cfd1a3feb14763f17714f52a56749d9925b7d7ba4806368dc414a342fc2","observation_id":"0530b2be-a988-417d-965b-467cb04fdfbb","resolution":{"observed_at":"2026-08-12T20:26:04.507147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.510960Z","title":"Lecuyer et al., ``Certified robustness to adversarial examples with differential privacy,'' in SP, 2019, pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.510960Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:1ceca456562251a90385c9c8d073463617e7384139ab0c7c3b647abde74ddc40","observation_id":"bed6b1c9-18c5-4581-b71b-115c443ba275","resolution":{"observed_at":"2026-08-12T20:26:04.510960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.515077Z","title":"Tsipras et al., ``Robustness may be at odds with accuracy,'' in ICLR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.515077Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:bf550b54d38403753e03254413982efade8eccbf77b698d049fbfeb5a32b1ea4","observation_id":"3a96a6ea-10ee-4077-9f5b-e7c0ef5a2135","resolution":{"observed_at":"2026-08-12T20:26:04.515077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.518985Z","title":"Nie et al., ``Diffusion models for adversarial purification,'' in ICML, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.518985Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:786577c87647013ed3367ae975442ab468d9caf35f9dc149a1dcc001d3f160ad","observation_id":"fbfd37d8-8df7-4554-b43b-4dd789d3f0c3","resolution":{"observed_at":"2026-08-12T20:26:04.518985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.522661Z","title":"Song et al., ``Pixeldefend: Leveraging generative models to understand and defend against adversarial examples,'' in ICLR, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.522661Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:0195013c85e9e681bd9052fd4a903db59ec8ceb7ae6e4944f350cc1123653e82","observation_id":"6f838a98-c636-4d18-baa3-783f6d989130","resolution":{"observed_at":"2026-08-12T20:26:04.522661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.526912Z","title":"Buckman et al., ``Thermometer encoding: One hot way to resist adversarial examples,'' in ICLR, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.526912Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:ce524791b5a8a6eb01d515061a295385e9bce0b8ef76efd9eec671396d4f6b60","observation_id":"54d070ab-d4af-452f-a6d4-398c787cb718","resolution":{"observed_at":"2026-08-12T20:26:04.526912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.530822Z","title":"Guo et al., ``Countering adversarial images using input transformations,'' in ICLR, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.530822Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:4c02911a46da98da36082775f12d232d84bcc83cc8e04dcc107bceaa02a0820d","observation_id":"7e74e280-4826-452a-bcef-9476ed8c24de","resolution":{"observed_at":"2026-08-12T20:26:04.530822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.02900","last_updated":"2017-05-08T14:55:32Z","snapshot_observed_at":"2026-08-14T14:06:11.856499Z","submitted_at":"2017-05-08T14:55:32Z","title":"Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.02900","snapshot_observed_at":"2026-08-12T20:26:04.534795Z","title":"Das et al., ``Keeping the bad guys out: Protecting and vaccinating deep learning with jpeg compression,'' in arXiv abs/1705.02900, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.534795Z"},"links":{"cited_paper":"/paper/1705.02900","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:17af52652ccafffb2d24534e5772f266a243ff66c7726c07097be1bc09974dbe","observation_id":"74d50ce6-869d-4d7d-bcf0-a4c804313ee4","resolution":{"observed_at":"2026-08-12T20:26:04.534795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.06280","last_updated":"2017-10-17T11:12:44Z","snapshot_observed_at":"2026-08-08T05:01:01.781486Z","submitted_at":"2017-02-21T07:03:11Z","title":"On the (Statistical) Detection of Adversarial Examples","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.06280","snapshot_observed_at":"2026-08-12T20:26:04.539180Z","title":"Grosse et al., ``On the (statistical) detection of adversarial examples,'' in arXiv:1702.06280, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.539180Z"},"links":{"cited_paper":"/paper/1702.06280","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3135e85f619d7ef0836194dd11540f8dd6198fce2c7ff3fa95a04c3c6315679d","observation_id":"f2d4dc72-59f8-4e28-97fe-a52d0641ca4e","resolution":{"observed_at":"2026-08-12T20:26:04.539180Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.543466Z","title":"Li et al., ``Backdoor learning: A survey,'' IEEE TNNLS, vol","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.543466Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:96a45922a95ae4a6363d77748ebae3915ba734ab16abcac892446af33d2223d1","observation_id":"a759da0b-8719-42b5-9949-337da20b583c","resolution":{"observed_at":"2026-08-12T20:26:04.543466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.547518Z","title":"Jia et al., ``Scalability vs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.547518Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:6c5aedda0f58dd73fbd7db691ec34e1fbd846fd56bd6b15f996a4e0d6bc57ebd","observation_id":"acc15e00-bd49-46af-ac62-75a5894e9a1d","resolution":{"observed_at":"2026-08-12T20:26:04.547518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.551621Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.551621Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3e1f22d9fef229b445b932d025559967302583def9e7da8f7aa2d973934d9a25","observation_id":"f02db6f3-a79a-4c9c-95af-fc3d11e87976","resolution":{"observed_at":"2026-08-12T20:26:04.551621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.555312Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.555312Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:fe2c7419414740c06c0d2846b371e60e1c0ea721b0f1154fed264e9ae3461857","observation_id":"a7add56b-09dd-4863-aa5d-7aaaf20e2450","resolution":{"observed_at":"2026-08-12T20:26:04.555312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.558967Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.558967Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:b9b0f7a9d48bed8a232249d700c7152834c5baf51e17c6a15d9cb596fcb7d9ea","observation_id":"f1512f1f-6a10-4802-b034-497bd95b3813","resolution":{"observed_at":"2026-08-12T20:26:04.558967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.03041","last_updated":"2018-02-08T20:34:19Z","snapshot_observed_at":"2026-08-10T10:03:25.197654Z","submitted_at":"2018-02-08T20:34:19Z","title":"Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.03041","snapshot_observed_at":"2026-08-12T20:26:04.562544Z","title":"Paudice et al., ``Detection of adversarial training examples in poisoning attacks through anomaly detection,'' in arXiv:1802.03041, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.562544Z"},"links":{"cited_paper":"/paper/1802.03041","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:36e4b3dbb554704d15aa38ebf340a7a4d4cb3c6894a7eb41c293e5f5e28c1556","observation_id":"f3d6f62c-5089-47e9-9362-4af27c716252","resolution":{"observed_at":"2026-08-12T20:26:04.562544Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.566644Z","title":"Tran et al., ``Spectral signatures in backdoor attacks,'' in NeurIPS, 2018, p","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.566644Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:379a2a81b8729fbf4ceff35089c85d64c19d32679a197a2b07337ece8fc44bd6","observation_id":"92a1067a-458f-4a76-98a2-ed6c3abcffb4","resolution":{"observed_at":"2026-08-12T20:26:04.566644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.570500Z","title":"Barreno et al., ``The security of machine learning,'' Machine Learning, vol","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.570500Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:61eadca92b58b518d46e427d10cacdb97648dcabd9e77abba921cff156583b9c","observation_id":"8afb7c85-b505-4c74-aad0-d4d952a4f76a","resolution":{"observed_at":"2026-08-12T20:26:04.570500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.574199Z","title":"Chen et al., ``Detecting backdoor attacks on deep neural networks by activation clustering,'' in SafeAI@AAAI, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.574199Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:da02cc8559b56f25d5bccc8a6893f3b7883c67215c0a72c532f3323fa9356cfa","observation_id":"886d473b-8ca6-4c6c-935c-8d0faa337276","resolution":{"observed_at":"2026-08-12T20:26:04.574199Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.577847Z","title":"Borgnia et al., ``Strong data augmentation sanitizes poisoning and backdoor attacks without an accuracy tradeoff,'' in ICASSP, 2021, pp","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.577847Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:9b7290c8505b3d349fea3ab40d31dc0bf4a5408f68ab814c881012825c5020de","observation_id":"7f770d63-05ec-4cb7-80c9-facfc343e06c","resolution":{"observed_at":"2026-08-12T20:26:04.577847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.581575Z","title":"Qiu et al., ``Deepsweep: An evaluation framework for mitigating dnn backdoor attacks using data augmentation,'' in AsiaCCS, 2021, p","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.581575Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:0034f229788b903ab728c7ba8e5afe130937650d4066e612650ceeaac93771b0","observation_id":"b548a750-9faa-49ed-91d7-34bc8af8c6e1","resolution":{"observed_at":"2026-08-12T20:26:04.581575Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.585246Z","title":"Li et al., ``Learning from noisy labels with distillation,'' in ICCV, 2017, pp","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.585246Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:5f9c15c786ded0610be5efebeecdca671799b7f26cfb2f37d3f44ba7c569603f","observation_id":"1ae73a0f-8a5c-4bb2-8dd3-cc8735d97ddb","resolution":{"observed_at":"2026-08-12T20:26:04.585246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.588930Z","title":"Diakonikolas et al., ``Sever: A robust meta-algorithm for stochastic optimization,'' in ICML, 2019, pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.588930Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:1cc00b313c43c7273fe0ab6773de3fd4cee7b7fde5f5003ee95e56597c54dd7e","observation_id":"f4c2eb9d-4525-4b83-950d-514d613fcaa4","resolution":{"observed_at":"2026-08-12T20:26:04.588930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.592517Z","title":"Zhu et al., ``Neural polarizer: A lightweight and effective backdoor defense via purifying poisoned features,'' in NeurIPS, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.592517Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:e27151cc67a0d5709c2eece6f757a9776574d35ba1e0417e78f68743032d6eb2","observation_id":"cecec702-1f25-4807-ba4a-daeeacdd6d3b","resolution":{"observed_at":"2026-08-12T20:26:04.592517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.595957Z","title":"Xu et al., ``L\\_dmi: An information-theoretic noise-robust loss function,'' in NeurIPS, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.595957Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:442fc6f40a02cc56f2dec70949450e4dc275b655000a6f008545730d4e05dd29","observation_id":"6a8873ed-cc48-4e98-8474-0508055e3727","resolution":{"observed_at":"2026-08-12T20:26:04.595957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.599616Z","title":"Liu and H","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.599616Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:b696de6529a02adba68918a8e963a22feb0b0d7cea8f553b655b66d30c84fd02","observation_id":"9fa024ee-4f9d-452a-84f6-a0efa28ecd7c","resolution":{"observed_at":"2026-08-12T20:26:04.599616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.603366Z","title":"Patrini et al., ``Making deep neural networks robust to label noise: A loss correction approach,'' in CVPR, 2017, pp","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.603366Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:fb64b1cd78c234c280e80eadc73eacc38e50b3d406cb2e3f3adaccdd1fa6eb66","observation_id":"5a20c93d-7d49-4aaf-9f41-b524d7eaaf4c","resolution":{"observed_at":"2026-08-12T20:26:04.603366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.607010Z","title":"Liu et al., ``Fine-pruning: Defending against backdooring attacks on deep neural networks,'' in RAID, 2018, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.607010Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3778d401824aea9026d8d6cc0687561c5e0b6bee894b7db6ca5c9b872746ca5c","observation_id":"2105b7a5-09e4-472b-a573-3cf25eaefa45","resolution":{"observed_at":"2026-08-12T20:26:04.607010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.610596Z","title":"Wu and Y","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.610596Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3756e13b63b6bd1f9c0639bf78e100f2b4580ce96be7a64cedff7907d5d53a75","observation_id":"a2edf771-0fe7-4ed1-96e7-323a6cfd99b0","resolution":{"observed_at":"2026-08-12T20:26:04.610596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.614155Z","title":"Zheng et al., ``Pre-activation distributions expose backdoor neurons,'' in NeurIPS, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.614155Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:b50215d71fc04937fb6390303e725ae9434137f451e08ea011f49c8ba146a069","observation_id":"e15002bd-7b64-4c58-9b36-fb5fad1c17f9","resolution":{"observed_at":"2026-08-12T20:26:04.614155Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.617830Z","title":"175--191","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.617830Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:8886515b15fd9499d38921dd61e436c53c9ae43e2abf73aee64211d2ef6fc526","observation_id":"99eacf46-97cd-459a-960a-3af2254fdafa","resolution":{"observed_at":"2026-08-12T20:26:04.617830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.621749Z","title":"Li et al., ``Reconstructive neuron pruning for backdoor defense,'' in ICML, 2023, pp","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.621749Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:786346d5e6aaccc5d216bc8106714ba1e0852c90a6918f1e91691fd129c665d5","observation_id":"66aa2a0f-99e0-4ada-ba26-8fd9369bf3e9","resolution":{"observed_at":"2026-08-12T20:26:04.621749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.625379Z","title":"Orekondy et al., ``Knockoff nets: Stealing functionality of black-box models,'' in CVPR, 2019, pp","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.625379Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:dbb2dccffe2a04490f002a1231e37471b9ac3e0024d5482050a4d35112272b6c","observation_id":"8bc8ec70-4569-4375-8de4-ac2285d2201c","resolution":{"observed_at":"2026-08-12T20:26:04.625379Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.629210Z","title":"Adi et al., ``Turning your weakness into a strength: Watermarking deep neural networks by backdooring,'' in USENIX Security, 2018, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.629210Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:614b554dba9d5809ecb56da468641aaeef4e3389a0dcc0e83c72a2999b1c5c40","observation_id":"ecd5401a-41ac-49f3-b3b7-fe809f399197","resolution":{"observed_at":"2026-08-12T20:26:04.629210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.632864Z","title":"Zhang et al., ``Protecting intellectual property of deep neural networks with watermarking,'' in AsiaCCS, 2018, p","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.632864Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:62d4e2a711d56296e14a713bb415551a8a1a8899d324aaec91e870cc67065fbf","observation_id":"af63f2dc-ddca-42a8-b0f5-a77c1eae8635","resolution":{"observed_at":"2026-08-12T20:26:04.632864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.636745Z","title":"Jia et al., ``Entangled watermarks as a defense against model extraction,'' in USENIX Security, 2021, pp","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.636745Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3c2311f325d78c7125e9ac81121d99222c16c2947e8b49f2e16575a0209e961a","observation_id":"a37ff1c4-12ac-4a3f-97de-bbe714345eb6","resolution":{"observed_at":"2026-08-12T20:26:04.636745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.640361Z","title":"Uchida et al., ``Embedding watermarks into deep neural networks,'' in ICMR, 2017, p","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.640361Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:9ca3320957244130d060af13fc637a9abd6e81c712053192ac9a999159ec2f5e","observation_id":"30f80730-ade6-41aa-8795-6399e1f7d7de","resolution":{"observed_at":"2026-08-12T20:26:04.640361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.643928Z","title":"Bansal et al., ``Certified neural network watermarks with randomized smoothing,'' in ICML, 2022, pp","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.643928Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:d2d8e37b2ec9125292118f0e9158af042637fe1cec9cd6e707bd36a108c0ad29","observation_id":"41d3b646-d1e7-46bf-b27c-efe27d2580ff","resolution":{"observed_at":"2026-08-12T20:26:04.643928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.647674Z","title":"Bagdasaryan and V","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.647674Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:fa8907ecbc7c17ed78d33d12bf511d8c032b4462dff180810f8d7948862a7677","observation_id":"a6e0f282-5f49-40cb-882e-f21f33c77cf3","resolution":{"observed_at":"2026-08-12T20:26:04.647674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.651410Z","title":"Szyller et al., ``Dawn: Dynamic adversarial watermarking of neural networks,'' in MM, 2021, p","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.651410Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:7f937c1932a1698791ecc44de8a16f30b4eba98809f8b5a2dfe6020da6bccb04","observation_id":"9f21b925-1904-4d11-a0bc-2a217e5d1a53","resolution":{"observed_at":"2026-08-12T20:26:04.651410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.655071Z","title":"Cao et al., ``Ipguard: Protecting intellectual property of deep neural networks via fingerprinting the classification boundary,'' in AsiaCCS, 2021, p","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.655071Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:13048f772d2a0bfb3bcfb50139ae380cfef84c4b6635784f629cb79d7f650311","observation_id":"07c9b905-876f-4de2-a4db-318bd9d79496","resolution":{"observed_at":"2026-08-12T20:26:04.655071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.658890Z","title":"Peng et al., ``Fingerprinting deep neural networks globally via universal adversarial perturbations,'' in CVPR, 2022, pp","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.658890Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:7ab65fbdb9cce49fd5d3495639c4e59a64fe89e0f97fa02e06b3316ec51bbab4","observation_id":"86049648-5417-417b-8d1b-02f8853f0b99","resolution":{"observed_at":"2026-08-12T20:26:04.658890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.662481Z","title":"Lukas et al., ``Deep neural network fingerprinting by conferrable adversarial examples,'' in ICLR, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.662481Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:4113eb9ebed13cbca1d6da2cd5b09ce81c234bc0d3c6e4bede1b5be7ccb96b79","observation_id":"76707076-d4ff-422d-9b6e-fb9757114c2d","resolution":{"observed_at":"2026-08-12T20:26:04.662481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.666029Z","title":"Zheng et al., ``A dnn fingerprint for non-repudiable model ownership identification and piracy detection,'' IEEE TIFS, vol","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.666029Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:0a1698ae68010aaacec9032843ce9f61f084e674a15793aad5e8b4206b111e8e","observation_id":"ed765983-042c-4d51-804d-20b1451bfa18","resolution":{"observed_at":"2026-08-12T20:26:04.666029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.669584Z","title":"Maini et al., ``Dataset inference: Ownership resolution in machine learning,'' in ICLR, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.669584Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:6ea2109a565866ab34e3bcb8cf8fa7e7eb59d38ca17b09a68838404f4c41f975","observation_id":"3e4a7a31-e52d-49e4-8cd8-0d4de3df74eb","resolution":{"observed_at":"2026-08-12T20:26:04.669584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.673144Z","title":"Sablayrolles et al., ``Radioactive data: tracing through training,'' in ICML, 2020, pp","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.673144Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:2c5d9e67633a09d04f9620bd872696107766ddd011a7b682ee4ff24e472f0a59","observation_id":"9dd9f144-3511-434c-a99e-9e2ac6349eea","resolution":{"observed_at":"2026-08-12T20:26:04.673144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.676872Z","title":"Huang et al., ``Unlearnable examples: Making personal data unexploitable,'' in ICLR, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.676872Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:34a6d3d3ea1172de997e2ad30d076663639e2bd5057d3d3cf145c5cc6dd13dad","observation_id":"7d896771-ff24-4c48-8da3-8bdc3e6202aa","resolution":{"observed_at":"2026-08-12T20:26:04.676872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.680648Z","title":"Wenger et al., `` SoK : Anti-facial recognition technology,'' in SP, 2023, pp","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.680648Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3e6ae31b4f8fc371062babc1aaacbdf380099066f6354045143fdbb3c05b208b","observation_id":"c6cb648d-8912-4438-8ebd-e2d5f3e9a7c5","resolution":{"observed_at":"2026-08-12T20:26:04.680648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.684472Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.684472Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:430dea41e408f6a42bdbddda86cfb604270dac21a27cc012d05fd917586ecdd0","observation_id":"9dd85a46-2c6c-42ed-a73e-ed714d342ccf","resolution":{"observed_at":"2026-08-12T20:26:04.684472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.688167Z","title":"Liu et al., ``Your model trains on my data? protecting intellectual property of training data via membership fingerprint authentication,'' IEEE TIFS, vol","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.688167Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:732c4c47b369f1b8922d090eeee71cfc60b2428053239b6c1c657fe7cf04b51e","observation_id":"3b536aff-f7c7-47f0-82af-15bbb72e8408","resolution":{"observed_at":"2026-08-12T20:26:04.688167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.691907Z","title":"Fredrikson et al., ``Model inversion attacks that exploit confidence information and basic countermeasures,'' in CCS, 2015, p","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.691907Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:475f0c1b36601be92f0e0b55644a970e4be11e01a8375a46120aa250bc741e4f","observation_id":"6ac4f318-cbe0-4e4c-9c18-9138fe139e8d","resolution":{"observed_at":"2026-08-12T20:26:04.691907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.695670Z","title":"Abadi et al., ``Deep learning with differential privacy,'' in CCS, 2016, pp","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.695670Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:3daf6679b542076668a758e1ea2d59abf979c6787699cecd70db68eab84b53cf","observation_id":"63c7273c-a5c2-4152-95f6-ad4edbf858d5","resolution":{"observed_at":"2026-08-12T20:26:04.695670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.699468Z","title":"Hu et al., `` SoK : Privacy-preserving data synthesis,'' in SP, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.699468Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:28ca42e18ade4a1dba85279d899186b6a887ce37acf1b20482ae7a4646b5deec","observation_id":"f56d328b-1592-41a9-91e9-c5a7ace42686","resolution":{"observed_at":"2026-08-12T20:26:04.699468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06739","last_updated":"2018-02-19T18:05:33Z","snapshot_observed_at":"2026-08-14T06:50:15.677632Z","submitted_at":"2018-02-19T18:05:33Z","title":"Differentially Private Generative Adversarial Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06739","snapshot_observed_at":"2026-08-12T20:26:04.703235Z","title":"Xie et al., ``Differentially private generative adversarial network,'' in ArXiv abs/1802.06739, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.703235Z"},"links":{"cited_paper":"/paper/1802.06739","citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:9ca12bbd5071680b7e49f7e72f44bc28dcfb16dcfefca1be4f2817c928d4c5da","observation_id":"b56ebd0b-19f2-4e91-afe1-bdb205b9b950","resolution":{"observed_at":"2026-08-12T20:26:04.703235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.707735Z","title":"Torkzadehmahani et al., ``Dp-cgan: Differentially private synthetic data and label generation,'' in CVPR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.707735Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:09eceb27a5985db9bd719c12888a0f22ed57f868ddc3d79ea1b452cad0f3a3f3","observation_id":"09099b20-bfa8-40f8-a7aa-73a33a299ded","resolution":{"observed_at":"2026-08-12T20:26:04.707735Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.711421Z","title":"Zheng and B","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.711421Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:db5f923e0b7c2fc8b2665130a3e6952883110b0e804fbbe39992c68a3594ae02","observation_id":"c2d89b87-ffa8-451a-a23c-923a57dbd7e9","resolution":{"observed_at":"2026-08-12T20:26:04.711421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.715238Z","title":"Papernot et al., ``Semi-supervised knowledge transfer for deep learning from private training data,'' in ICLR, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.715238Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:97ebb244ada0c76881b5ae2131f0d5e620f3fbe069d9ab393c9efe859c5cfb7f","observation_id":"c914f13c-1ae8-44ee-81f8-2263df30b550","resolution":{"observed_at":"2026-08-12T20:26:04.715238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.719499Z","title":"Jayaraman and D","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.719499Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:514b5e80c7db9156f2b8d99d20ac3efd3355e1beb4ebb81009a19ffdae799bc6","observation_id":"fc499850-fcf5-4969-a58c-bd68966a2d33","resolution":{"observed_at":"2026-08-12T20:26:04.719499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.723260Z","title":"Chaudhuri et al., ``Differentially private empirical risk minimization.'' JMLR, vol","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.723260Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:c66f3e0575b0db9c37fe7c61f4c27aba2ff87d6c1c93c36380ae78628ed02bf6","observation_id":"96d8f0cf-7e7f-42b0-92ea-141a4d130d0a","resolution":{"observed_at":"2026-08-12T20:26:04.723260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.726994Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.726994Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:8a2eac4e7621f38277922bd955005c24bd323130bc71a4b18ef863d7348dfc3d","observation_id":"affbd966-cf30-4e46-a0b6-43e63e6131bc","resolution":{"observed_at":"2026-08-12T20:26:04.726994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.730616Z","title":"Hardt, E","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.730616Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:7f464bfb4f848751b2a70b70bbce75999be956ead14c5897aceae84a9270b697","observation_id":"b6b122e4-366a-42b4-9d15-fae8811279fc","resolution":{"observed_at":"2026-08-12T20:26:04.730616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.734377Z","title":"Kamiran and T","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.734377Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:a0871faa7eae12bb7f4b8a55449d8c2a357dad771f3d97227c4fbc1fbb8b8a4f","observation_id":"76539f15-08e7-42b3-9a99-9287776646cf","resolution":{"observed_at":"2026-08-12T20:26:04.734377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.737851Z","title":"Calmon et al., ``Optimized pre-processing for discrimination prevention,'' in NeurIPS, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.737851Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:590ffb1b514e5f73ea98a81983fddbca2a33a0ea022780a47adcfb9e3854e80c","observation_id":"98192fda-d480-4839-aecc-6d809dd5559f","resolution":{"observed_at":"2026-08-12T20:26:04.737851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.741654Z","title":"Zemel et al., ``Learning fair representations,'' in ICML, 2013, pp","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.741654Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:8a0ae26077f870d43cb5ddb1c1cd364ad87da04344c862f5b580121e5dbcc37c","observation_id":"621fff55-3665-4be4-8f81-9ab0d870ea48","resolution":{"observed_at":"2026-08-12T20:26:04.741654Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.745355Z","title":"Feldman, S","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.745355Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:d157ced0173295b3604dd08da7e8fd0348b3d1b4a45102520eb39b98869118fa","observation_id":"56f085c9-12e0-4401-ac87-a51d570f22f8","resolution":{"observed_at":"2026-08-12T20:26:04.745355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.749326Z","title":"Agarwal et al., ``A reductions approach to fair classification,'' in ICML, 2018, pp","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.749326Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:03509bc17f094d8b6ca9626c8e02abcb62c4a41a539bbe419b1acdf54f541218","observation_id":"a7ea1405-26ca-498b-9818-42f9ac1bba78","resolution":{"observed_at":"2026-08-12T20:26:04.749326Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.752861Z","title":"120--129","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.752861Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:e3dc1babffe783a9a439e72c12dcb40c90034fb138ab0459e918a81085e2c85d","observation_id":"c2d8e682-f777-4071-a237-8b45d49112f9","resolution":{"observed_at":"2026-08-12T20:26:04.752861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.756501Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.756501Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:96d5e7950d784e07eb6f84d4c723a92d1bd948e28150c109d98eea57df0607ea","observation_id":"25a8684e-913e-48e7-9849-9dc6139641ed","resolution":{"observed_at":"2026-08-12T20:26:04.756501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.760158Z","title":"Kamishima et al., ``Fairness-aware classifier with prejudice remover regularizer,'' in Machine Learning and Knowledge Discovery in Databases, 2012, pp","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.760158Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:a00e121a3677bec26d246c3df2394631576748bc37ddc9e0deaaed1cdd135679","observation_id":"9d2ca1f6-7fc0-4ea1-8560-92809c0aa2f6","resolution":{"observed_at":"2026-08-12T20:26:04.760158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.763769Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.763769Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:213b0c461e0c943bba5958d5052cb499d67a0f8e8fd07549224da62bcd29652d","observation_id":"21e6004a-8bf3-443e-ba39-53b0a391c6ed","resolution":{"observed_at":"2026-08-12T20:26:04.763769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.768250Z","title":"Louppe et al., ``Learning to pivot with adversarial networks,'' in NeurIPS, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.768250Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:aef5e7621e7ac8845143954708a1767b3c1ec1a7a381057935ef67f5c92c28de","observation_id":"dbd7c46a-0806-4567-9063-e99cb40832b6","resolution":{"observed_at":"2026-08-12T20:26:04.768250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.771925Z","title":"Pinz\\' o n, C","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.771925Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:8a1eb444fba701dbd2a7d9e56d6512d4ec37ca6d9b07161bb8c56e50e4e7dac4","observation_id":"4403d5b9-a181-44cd-b32c-76b3fe62d943","resolution":{"observed_at":"2026-08-12T20:26:04.771925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.775481Z","title":"Pleiss et al., ``On fairness and calibration,'' in NeurIPS, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.775481Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:323554e9c0b696233f94c0437596e3f6dadbdd868d1bef7bf2da0f251102dde5","observation_id":"d2d7c354-617a-44de-9fba-8ff71b3e0388","resolution":{"observed_at":"2026-08-12T20:26:04.775481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.779374Z","title":"Kamiran, A","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.779374Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:79f6e40c4f8b7400b3d9835a7949c4b72f134d888bb1a5927fec4928c19ade44","observation_id":"ebdd35cd-5c98-4428-98d9-61a617611dfc","resolution":{"observed_at":"2026-08-12T20:26:04.779374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.783193Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.783193Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:f523948cd68ae73acfc97d011e548035e96b7df35e3fe4ba91590075f207a101","observation_id":"161c3269-f4b0-4a1d-9754-c3715aca1d7e","resolution":{"observed_at":"2026-08-12T20:26:04.783193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:26:04.786976Z","title":"Salvador et al., ``Faircal: Fairness calibration for face verification,'' in ICLR, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts","version":2},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-12T20:26:04.786976Z"},"links":{"citing_paper":"/paper/2411.09776"},"observation_digest":"sha256:27b4744ff4cd7d4f8ebef3f19924f936b78c5b9b1d31a61b542b7bb96868cfaf","observation_id":"8b0f9a01-497d-417b-8bba-3931543c8214","resolution":{"observed_at":"2026-08-12T20:26:04.786976Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.09776","last_updated":"2025-08-14T17:44:57Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-12T22:03:14.658935Z","submitted_at":"2024-11-14T19:41:51Z","title":"Combining Machine Learning Defenses without Conflicts"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":100,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":191},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 100 of 191 outbound references and 1 inbound Pith citation observation for arXiv:2411.09776."}