{"as_of":"2026-08-09T06:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a146708d1677db93a1b259b73f031f6ce8e3e627cc58f9fb31557cc91d593bf2","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T14:06:54.760402Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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":"2026-05-17T20:08:21.578954Z","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":"2026-05-17T20:10:10.948942Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"cited_work":{"arxiv_id":"2502.07011","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.07011","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Drop: Poison dilution via knowledge distillation for federated learning","venue":null,"work_id":"b3cabf78-1695-4736-80cb-367820d86cd2","year":2025},"citing_paper":{"arxiv_id":"2511.14715","last_updated":"2026-05-12T06:00:59Z","snapshot_observed_at":"2026-08-04T15:37:33.366495Z","submitted_at":"2025-11-18T17:57:40Z","title":"FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-17T20:08:21.578954Z"},"links":{"cited_paper":"/paper/2502.07011","citing_paper":"/paper/2511.14715"},"observation_digest":"sha256:7d66952d68e5c05fabd8371d3fddb92b49e9396b7391d1a694bfdc6023f37963","observation_id":"5ce3903b-102a-4ed8-a747-1901d1012487","resolution":{"observed_at":"2026-05-17T20:10:10.950799Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.07011/citation-record","integrity":"/paper/2502.07011/integrity","json":"/paper/2502.07011/citation-record.json","paper":"/paper/2502.07011"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.20456","last_updated":"2024-05-30T20:10:24Z","snapshot_observed_at":"2026-08-02T17:45:21.507429Z","submitted_at":"2024-05-30T20:10:24Z","title":"Scaling Laws for the Value of Individual Data Points in Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20456","snapshot_observed_at":"2026-08-08T14:06:54.588630Z","title":"Scaling laws for the value of individual data points in machine learning,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.588630Z"},"links":{"cited_paper":"/paper/2405.20456","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:e88a54ab608f6f625b17d470a6e7bdabde440133f696021ae424f469e3b5b331","observation_id":"5d21d3c8-8d97-4a84-96f2-a386fc92e20a","resolution":{"observed_at":"2026-08-08T14:06:54.588630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.975597Z","title":"Realizing petabyte scale acoustic modeling,","venue":null,"work_id":"71b069ed-88c5-49d7-a734-6bdb36513d7c","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.595052Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:25dcce721a43350570b747b10c3a478fef80f41a406af958c6de02ded27595ab","observation_id":"b0ef749c-5879-4d78-bcb7-21297d397cd5","resolution":{"observed_at":"2026-08-08T14:06:55.978327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.614604Z","title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection,","venue":null,"work_id":"670c0759-04e2-4919-81f1-54e76c7691ec","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.600854Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:4fc21cbf7e9c0d1a58bb1c9132e640b4bff4f91299aaa234bed2c4248832de27","observation_id":"6fecac3f-20fc-47b7-8d3a-493fd01fa3ad","resolution":{"observed_at":"2026-08-08T14:06:55.618600Z","resolver_source":"arxiv_id_nonexistent","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.00364","last_updated":"2022-01-09T19:03:39Z","snapshot_observed_at":"2026-07-06T12:03:48.844241Z","submitted_at":"2021-10-30T23:36:10Z","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.00364","snapshot_observed_at":"2026-08-08T14:06:54.603277Z","title":"Sustainable ai: Environmental implications, challenges and opportunities,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.603277Z"},"links":{"cited_paper":"/paper/2111.00364","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:41cfef0a47ead579d4f71fd060fcad984566aab9791e39ee80d18aa096a8876c","observation_id":"f6ff712d-4d16-4351-8262-472ababa84d4","resolution":{"observed_at":"2026-08-08T14:06:54.603277Z","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":"2026-08-08T14:06:54.606871Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.606871Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:aa05e1b7d5ddd05c89895880133c997b0e6bef591f90e80145d745ddb1cae827","observation_id":"3cce1aeb-b187-44b4-b6eb-f86908b6bcc3","resolution":{"observed_at":"2026-08-08T14:06:54.606871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.954352Z","title":"Bad- nets: Evaluating backdooring attacks on deep neural networks,","venue":null,"work_id":"26914495-f1aa-4d5a-b959-d944284cb18c","year":2019},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.609832Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:dc9fbdfbe46f6116c6de25e15087bdecf0d2b9d0c7fce364e26338f3235b92ba","observation_id":"bdcbd498-da37-4435-9e91-f174697f8720","resolution":{"observed_at":"2026-08-08T14:06:55.957737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10884","last_updated":"2024-06-16T10:31:45Z","snapshot_observed_at":"2026-07-06T18:31:40.910349Z","submitted_at":"2024-06-16T10:31:45Z","title":"Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10884","snapshot_observed_at":"2026-08-08T14:06:54.612339Z","title":"Linkage on security, privacy and fairness in federated learning: New balances and new perspectives,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.612339Z"},"links":{"cited_paper":"/paper/2406.10884","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:b674b9eb7df6d51bd82f36161c2a438eac32e27738107114f1390ed450fd0bdd","observation_id":"9f2ce43a-b719-4a2f-aa0e-9357f4cfaed5","resolution":{"observed_at":"2026-08-08T14:06:54.612339Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.00459","last_updated":"2019-08-06T04:36:45Z","snapshot_observed_at":"2026-08-07T03:33:38.635570Z","submitted_at":"2018-07-02T04:37:43Z","title":"How To Backdoor Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.00459","snapshot_observed_at":"2026-08-08T14:06:54.615421Z","title":"How to backdoor federated learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.615421Z"},"links":{"cited_paper":"/paper/1807.00459","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:f9ebf17340b2a58ed273a8747f3a1c6bbc0c47c5dd2503993380d2cb5000ee3a","observation_id":"3bea6b1d-401f-48d9-9cd8-3c08f97a9576","resolution":{"observed_at":"2026-08-08T14:06:54.615421Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.947765Z","title":"Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses,","venue":null,"work_id":"76f868d6-2d90-44fb-8c0d-573a34f9ef2d","year":2020},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.619024Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:885d8a2f54c0cda04ef8006f55bab0a8386f4559dac50fbf45712f67237002f6","observation_id":"9b722d2c-c493-4176-a6e6-cb98fb1c4680","resolution":{"observed_at":"2026-08-08T14:06:55.950145Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.940473Z","title":"Trojaning attack on neural networks,","venue":null,"work_id":"68a5e4f2-1cbd-4be0-b3fc-1272f8e0cb90","year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.621738Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:a9cd7ebd6f0832c78421ab2636101fc40004e9e663e12f62ba1f74743774cf2c","observation_id":"aceaf075-185e-44ec-8a6a-7285bad9796f","resolution":{"observed_at":"2026-08-08T14:06:55.942746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.931763Z","title":"Get rid of your trail: Remotely erasing backdoors in federated learning,","venue":null,"work_id":"9a61ef82-33ac-48b0-b03d-cae272b6ecc2","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.624724Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:42cc5d5c04a41a6273a1f2f6a9be02cdad2acc923cbd6cb8fccfe47bff2cc8ab","observation_id":"a35fed71-86e3-49f1-be29-bbb53908c39e","resolution":{"observed_at":"2026-08-08T14:06:55.934635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06206","last_updated":"2024-09-09T22:11:39Z","snapshot_observed_at":"2026-08-04T01:54:15.690724Z","submitted_at":"2024-05-10T02:44:25Z","title":"Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning","version":2},"cited_work":{"arxiv_id":"2405.06206","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.06206","snapshot_observed_at":"2026-08-08T14:06:55.390548Z","title":"Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning","venue":"cs.CR","work_id":"1103d074-3b1e-4502-afea-6e79c76c5540","year":2024},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.626980Z"},"links":{"cited_paper":"/paper/2405.06206","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:d0a8cc65f66032914655d1af59bdefd856355c06fbf94f1044d9ac8e56c2aeed","observation_id":"e9492b6a-ba23-4b8e-81e4-a801cafc3f17","resolution":{"observed_at":"2026-08-08T14:06:55.393499Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.917497Z","title":"A survey for federated learning evaluations: Goals and measures,","venue":null,"work_id":"ee653e43-338a-470a-b149-50cbbe547108","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.632277Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:cfc167d96c7d6470a50c17c540738ea7611365a2d7bc9c22884428816976b3d8","observation_id":"f3ff8fa4-7288-4133-99cb-e9ff8809f13a","resolution":{"observed_at":"2026-08-08T14:06:55.920229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.900736Z","title":"Certified robustness to label-flipping attacks via ran- domized smoothing,","venue":null,"work_id":"b8be308a-ac12-477d-b14c-ae96955612f0","year":2020},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.637769Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:f5559e9c32184dec6aa6c7e5cd1bab12673c23e0609ac899b73aed00ffaf02d1","observation_id":"38862f54-c623-4780-91f3-61139614e0c7","resolution":{"observed_at":"2026-08-08T14:06:55.903582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.925588Z","title":"Available: https://api.semanticscholar","venue":null,"work_id":"e4b0de4c-a10e-482c-818c-693216252070","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.629868Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:6cd04c98b05e4b81280d006890afbd92bf3e3ebed03ba9c0d8717c785c4e4b62","observation_id":"6fc5d795-e882-41e8-8a47-9733eb1b63b5","resolution":{"observed_at":"2026-08-08T14:06:55.927816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.893136Z","title":"Local model poisoning attacks to Byzantine-Robust federated learning,","venue":null,"work_id":"bf94127c-bde7-405a-ba51-05af48f81a0a","year":2020},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.643110Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:84d7d31b6ccc6cb9fc191384bf79ef6d74119664a0ba05679f214b5a2bc15752","observation_id":"59854719-b6e1-4a07-b74e-581186da03d5","resolution":{"observed_at":"2026-08-08T14:06:55.895902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.885860Z","title":"Data poisoning attacks against federated learning systems,","venue":null,"work_id":"82dcf50f-334b-4eec-a33d-4c5edd9b4303","year":2020},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.645376Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:a4aeedb6b9ac4494fcdac02cc1eb33af9f5fa54cdaf89b99dc430f076595f088","observation_id":"3b7fd147-497a-4008-863d-c9f9ac0916de","resolution":{"observed_at":"2026-08-08T14:06:55.888401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.878129Z","title":"Byzantine- robust distributed learning: Towards optimal statistical rates,","venue":null,"work_id":"fb0e2552-2b90-4537-a57c-7f6a96922cb3","year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.647713Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:e34700a29caae733a14a81d0a795100211fed0802248ba831780f153e60e4d9e","observation_id":"856007b2-c68e-442e-ac62-3c0b4daced23","resolution":{"observed_at":"2026-08-08T14:06:55.880516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1206.6389","last_updated":"2013-03-25T10:16:36Z","snapshot_observed_at":"2026-07-06T02:50:47.096675Z","submitted_at":"2012-06-27T19:59:59Z","title":"Poisoning Attacks against Support Vector Machines","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.6389","snapshot_observed_at":"2026-08-08T14:06:54.640262Z","title":"Poisoning attacks against support vector machines,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.640262Z"},"links":{"cited_paper":"/paper/1206.6389","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:5c89f5a1d5bb4572248aeea367b2db90754ae824b4ab2afcc02826e1774dc709","observation_id":"e4f05905-03ff-4fb7-a432-9d2cb1e9222f","resolution":{"observed_at":"2026-08-08T14:06:54.640262Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.859798Z","title":"FLTrust: Byzantine-robust federated learning via trust bootstrap- ping,","venue":null,"work_id":"bad52f5b-913b-4aac-94e7-0cfe5643e592","year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.653287Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:0a7a2ab54682f1a31efd05b654108862e96e0202c5470fa55b0e7e8fb86c4855","observation_id":"826b5c54-d033-4417-a0bd-1e3b307a288a","resolution":{"observed_at":"2026-08-08T14:06:55.862500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1808.04866","last_updated":"2020-07-15T15:35:17Z","snapshot_observed_at":"2026-08-06T06:11:20.847532Z","submitted_at":"2018-08-14T19:20:35Z","title":"Mitigating Sybils in Federated Learning Poisoning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.04866","snapshot_observed_at":"2026-08-08T14:06:54.655391Z","title":"Mitigating sybils in federated learning poisoning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.655391Z"},"links":{"cited_paper":"/paper/1808.04866","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:4ada59df837785d8b3fa7283b4fce5e6d5b955ad28204f7b5346a57a361d09c1","observation_id":"e5cf528a-5361-42e1-929c-938b47fac33f","resolution":{"observed_at":"2026-08-08T14:06:54.655391Z","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":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.365460Z","title":"Auror: defending against poisoning attacks in collaborative deep learning systems,","venue":null,"work_id":"a0fdf05e-79df-477a-bf31-1f1dc3955be4","year":2016},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.658971Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:47dd27ef4dae07042ec5337be49b1edc1056e37351527a74a06c4c663cc88878","observation_id":"8df0902a-51e9-4e8c-b9b1-0869ece79d83","resolution":{"observed_at":"2026-08-08T14:06:55.368023Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.869631Z","title":"Machine learning with adversaries: Byzan- tine tolerant gradient descent,","venue":null,"work_id":"f6cd5acd-3d43-41f6-9146-9ca0e110a989","year":2017},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.650527Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:89012812548c8ec96d2ffda12bf820e6f082c4e05f4c254573a033a40f3c6e53","observation_id":"a08000ee-8624-4da4-9031-a8f35c7e8dfa","resolution":{"observed_at":"2026-08-08T14:06:55.872245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.842761Z","title":"{FLAME}: Taming backdoors in federated learning,","venue":null,"work_id":"a5847f52-2d8e-4601-8f75-69d390d023ca","year":2022},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.664615Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:532dec1ef8cca79864cf579ae252fcdea501b205ba2e84a4f54de9278907ef5d","observation_id":"be6ddbe9-9f1d-4af8-a534-7da87fb0d74c","resolution":{"observed_at":"2026-08-08T14:06:55.845596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.835883Z","title":"Flip: A provable defense framework for backdoor mitigation in federated learning,","venue":null,"work_id":"4ae40b58-35a8-48fd-86a9-d54151320f3c","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.667537Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:091de4d08ca49673be1dc8ee6acb3267d7690196a9528e97d25465f875f1acb6","observation_id":"03c3464a-12d9-4bb2-a3bc-cab59c32e2c3","resolution":{"observed_at":"2026-08-08T14:06:55.838382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.184886Z","title":"Mesas: Poisoning defense for federated learning resilient against adaptive attackers,","venue":null,"work_id":"0e21045d-1b50-4239-96b0-86dc2527a6cd","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.669995Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:825702c2e50ca76f03077bf90d16c67f6772be53ad32364b8a8f71afa6f58214","observation_id":"25c7b020-77b2-4f32-a6bb-de13e2396f8c","resolution":{"observed_at":"2026-08-08T14:06:55.187798Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.850730Z","title":"Flare: defending federated learning against model poisoning attacks via latent space representations,","venue":null,"work_id":"7b2298b9-cb13-496d-a414-b28695b0006f","year":2022},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.661666Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:a99b0596910763a3beffc602c5cb0527ff0ecc4a335d48a2e4bf1bba345bfda3","observation_id":"fd3a0649-e205-4f59-8930-9d83fafb09c1","resolution":{"observed_at":"2026-08-08T14:06:55.853689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:54.674949Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.674949Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:9529a3f60a199e3a4438cec4a00cf4384c1f5de28a5ebe142419b21b3e2f3102","observation_id":"d5dc3831-6f26-4fcc-8867-1c8dc98ede76","resolution":{"observed_at":"2026-08-08T14:06:54.674949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.816756Z","title":"Manipulating machine learning: Poisoning attacks and countermeasures for regression learning,","venue":null,"work_id":"511f8cc2-811e-4191-bd9e-bd0c2c7e6b99","year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.677135Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:de4e048e9f9670658920df288850e377539913ad65384d772ee2062543a0651b","observation_id":"f9404f0b-9860-4e78-9724-cc88c78f00ae","resolution":{"observed_at":"2026-08-08T14:06:55.819590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.806545Z","title":"Using machine teaching to identify optimal training-set attacks on machine learners,","venue":null,"work_id":"019950d9-8882-47a3-a005-c930ec33c70f","year":2015},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.679442Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:783b01ce3cd1a5f4ee16d99f8d5de933a2d78aed8e93ee38e416c67e9fb2154a","observation_id":"6551f7df-e17e-45b7-9c85-c3260d307b73","resolution":{"observed_at":"2026-08-08T14:06:55.810318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.828390Z","title":"On the pitfalls of security evaluation of robust federated learning,","venue":null,"work_id":"7af13d0d-9d43-44cc-863c-3dc38ff73bd7","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.672339Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:3f5224760a8b5643b8360d1f33be21072cbe167dcccfa90300ed92cb52a93f7e","observation_id":"9f52a3d6-73e7-4636-875a-bdf4cfbd6851","resolution":{"observed_at":"2026-08-08T14:06:55.830945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.787202Z","title":"Manipulating the byzantine: Optimizing model poisoning attacks and de- fenses for federated learning,","venue":null,"work_id":"9f57f933-58c7-479d-9c10-d0b74b1e4289","year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.684005Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:5672308608f0f2f19d5f5eb7515c5fc33b100f4e2646c997d5890a48ec03caac","observation_id":"43b3aeb0-bf50-4f64-89a4-0ea0c6bdf964","resolution":{"observed_at":"2026-08-08T14:06:55.790107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.779585Z","title":"Understanding black-box predictions via influence functions,","venue":null,"work_id":"5ae12c71-875e-447c-a368-a7cda535d78a","year":2017},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.686309Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:b43e330ae98cd99c31c28a3ff4568e8237fd4ac499a8fc36b037f2a2ca3f6150","observation_id":"e980a83a-b632-4571-897d-9929ab080dd2","resolution":{"observed_at":"2026-08-08T14:06:55.782114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.771738Z","title":"Poison frogs! targeted clean-label poisoning attacks on neural networks,","venue":null,"work_id":"ed47661f-4375-4298-9ed9-9c95bbb55669","year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.688189Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:360a8390435a559e59c35926aa493f27bed4934a740958f50bb54617fa3c71ec","observation_id":"83636c31-5a6d-4e81-b682-22c4cb904486","resolution":{"observed_at":"2026-08-08T14:06:55.774199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.796839Z","title":"Is feature selection secure against training data poisoning?","venue":null,"work_id":"19937891-7cd2-403e-85e7-c80b8badbdd8","year":2015},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.681924Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:b65690d2dc7f51dbe7fc9540af93714e1c0487c29f0fb9e14e848f7037a84360","observation_id":"397ae3db-f6b6-4c14-a440-feb1a1824938","resolution":{"observed_at":"2026-08-08T14:06:55.800214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.755212Z","title":"Attack of the tails: Yes, you really can backdoor federated learning,","venue":null,"work_id":"84c16c05-6e59-4c0f-88a7-0913bee6e688","year":2020},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.692167Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:28f81b532f7cca2d2e02b76fede5bc877af793a57cbec912381e39139442d113","observation_id":"e81fd54d-ef12-4ace-9421-986f32ea6039","resolution":{"observed_at":"2026-08-08T14:06:55.758222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07963","last_updated":"2019-12-02T19:00:11Z","snapshot_observed_at":"2026-08-06T20:09:23.048652Z","submitted_at":"2019-11-18T21:25:03Z","title":"Can You Really Backdoor Federated Learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.07963","snapshot_observed_at":"2026-08-08T14:06:54.694452Z","title":"Can you really backdoor federated learning?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.694452Z"},"links":{"cited_paper":"/paper/1911.07963","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:6a4a2547ec83603a85c16dd240fd0702aca93fa576079b3e3b14b5a6fdf8846a","observation_id":"5c97023e-e1df-4a73-845e-d9ea58657a0a","resolution":{"observed_at":"2026-08-08T14:06:54.694452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-08T14:06:54.697141Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.697141Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:dcb5ea7d5e3344d0ed5c1c365e517a3b800acd74ee11ac4657c5d0b5f9463dde","observation_id":"2b37bad6-76af-446e-87eb-e76e4bf22290","resolution":{"observed_at":"2026-08-08T14:06:54.697141Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.763165Z","title":"When does machine learning FAIL? generalized transferability for evasion and poisoning attacks,","venue":null,"work_id":"91ae75b0-b987-413b-aeed-87cbb78a1001","year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.690198Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:2f23f26f7d3823247394eb46cc4856592b83628e39943a91e49cab80caa6a089","observation_id":"1d4cf67d-d710-4e0f-9714-1cfb64954bc5","resolution":{"observed_at":"2026-08-08T14:06:55.766687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1109.2378","last_updated":"2011-09-12T05:49:11Z","snapshot_observed_at":"2026-08-03T18:17:29.793532Z","submitted_at":"2011-09-12T05:49:11Z","title":"Modern hierarchical, agglomerative clustering algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1109.2378","snapshot_observed_at":"2026-08-08T14:06:54.702296Z","title":"Modern hierarchical, agglomerative clustering algorithms,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.702296Z"},"links":{"cited_paper":"/paper/1109.2378","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:afeed4a282baf6adb4352609bfc7f3fab6fe44c8dfc0bf3b8ddf5023ba36b348","observation_id":"20b07886-4981-432a-8842-1edda5981cfa","resolution":{"observed_at":"2026-08-08T14:06:54.702296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.741975Z","title":"Baybfed: Bayesian backdoor defense for federated learning,","venue":null,"work_id":"19168d31-f31d-4cc2-b432-da9be04dc226","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.704558Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:f918fd200656a04d0f4defa8b918410aad4764e4f528b82d069ab92ab3b575bf","observation_id":"b833d80e-878e-4ba8-9c62-0187ec00fdc1","resolution":{"observed_at":"2026-08-08T14:06:55.744750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.733138Z","title":"Density- based clustering based on hierarchical density estimates,","venue":null,"work_id":"c004b193-6aad-4b78-8bd3-ff12834deb4f","year":2013},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.707622Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:2fb4a417584e756c2aa2d6736bb9f337758a1d40456600f2592ea359d568e6be","observation_id":"5be04ebd-9af1-4b89-84a7-c8d369ff07fe","resolution":{"observed_at":"2026-08-08T14:06:55.736026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:54.700261Z","title":"Robust aggregation for federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.700261Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:c9438f8b6f2855d5c3960e6f8e1fde5452fd8d4d7d6deb2ecf6905f71636261a","observation_id":"abcce5de-5b53-4c9e-8016-8872c1bcfb29","resolution":{"observed_at":"2026-08-08T14:06:54.700261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.724772Z","title":"Maze: Data-free model stealing attack using zeroth-order gradi- ent estimation,","venue":null,"work_id":"b77272a6-75dd-4f0f-93a2-e4188b173c11","year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.712222Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:b0981959b5f77a0fc1fa7d4c5557fedb13acb63acc1ef296c7b548d4f15cdf6e","observation_id":"be84c47d-0534-4371-9362-4c725bbd4a93","resolution":{"observed_at":"2026-08-08T14:06:55.727481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:54.714494Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.714494Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:ad8a378c3cc2866c7236926132df7b3a80e5f8d0557bdb1391441c6666912452","observation_id":"f394fc7f-f261-4287-8bd6-39c6c2f6c60d","resolution":{"observed_at":"2026-08-08T14:06:54.714494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.712392Z","title":"Unsupervised rep- resentation learning with deep convolutional generative adversarial networks,","venue":null,"work_id":"5e6ce4a0-ee56-47bd-97e9-983e5f36a725","year":2016},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.716635Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:404166875241dbd4caa00f9e0ec9c651a644290039bd2442c3a9599d32f7981b","observation_id":"988ae2ce-4311-4d8a-8a1c-2dd7e3cf33ce","resolution":{"observed_at":"2026-08-08T14:06:55.714999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.013856Z","title":"Hierarchical grouping to optimize an objective function,","venue":null,"work_id":"2b396a99-21f2-41d3-85ab-1a603ae682dd","year":1963},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.709833Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:09843c3105be250d3ded1f5fbda4cd0a593a269a78fbfb14cca4dd5ed8f16fc2","observation_id":"5670c8fc-b221-4ceb-940a-768fe00eff97","resolution":{"observed_at":"2026-08-08T14:06:55.016375Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:54.721618Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.721618Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:1b5aa0dc9ccb63046cfe30397c2e0a85141d710fb97df52ed76a905e6cfe8cd4","observation_id":"0be03bf0-6886-4586-be62-b21b4ce616a0","resolution":{"observed_at":"2026-08-08T14:06:54.721618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.03505","last_updated":"2018-10-02T21:20:09Z","snapshot_observed_at":"2026-08-07T01:38:08.346703Z","submitted_at":"2018-10-02T21:20:09Z","title":"CINIC-10 is not ImageNet or CIFAR-10","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.03505","snapshot_observed_at":"2026-08-08T14:06:54.723992Z","title":"Cinic-10 is not imagenet or cifar-10,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.723992Z"},"links":{"cited_paper":"/paper/1810.03505","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:cb3d4d587ea4e39d8a05a8ee35697075a55636533dc10bf07aa8d0872062ab0d","observation_id":"08065780-7133-49aa-8b58-2f51087ba4b7","resolution":{"observed_at":"2026-08-08T14:06:54.723992Z","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":"2026-08-08T14:06:54.726448Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.726448Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:9e0df1c85791146c83188c05a625719600d2940ff7dc3bc37ad8cedd3982d86e","observation_id":"89461b38-cf91-41f9-aa6a-ec2c3617186b","resolution":{"observed_at":"2026-08-08T14:06:54.726448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.705349Z","title":"Data-free model extraction,","venue":null,"work_id":"8e031b55-53be-413e-8264-29c73678e8b5","year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.719092Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:27f190364e1fc1ce097b770bbd1dea2e9cce129d4ac05065e69b640dc503b4fd","observation_id":"0e6aa47b-4546-4901-ac15-9c64879cfe05","resolution":{"observed_at":"2026-08-08T14:06:55.707946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.683047Z","title":"The mnist database of handwritten digit im- ages for machine learning research [best of the web],","venue":null,"work_id":"e8145e5e-69a7-464f-8e76-dba6097aed99","year":2012},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.731019Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:3f94626ca9ce0ae3a2ef08a9bed7b527b87d161eb43aac9445920351cf8cf0df","observation_id":"6de31b0a-a8ab-4dfe-ac44-dcdf2b1885d8","resolution":{"observed_at":"2026-08-08T14:06:55.685843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:54.733388Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.733388Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:e9cd930219b3f2803db64b48d9ed1d3af779a4dc3edb4662d6ff5b053a980f9b","observation_id":"bef857c7-20f5-402a-b7f4-7b2b15ba7675","resolution":{"observed_at":"2026-08-08T14:06:54.733388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.02079","last_updated":"2021-10-28T15:22:21Z","snapshot_observed_at":"2026-08-09T02:19:17.266233Z","submitted_at":"2021-02-03T14:29:09Z","title":"Federated Learning on Non-IID Data Silos: An Experimental Study","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.02079","snapshot_observed_at":"2026-08-08T14:06:54.735418Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.735418Z"},"links":{"cited_paper":"/paper/2102.02079","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:4a91084aaba661c59aaa6f37c4e6621fe326cf8b7d683683a4c1db4419132916","observation_id":"03ce907f-f1b6-477a-876c-da6ccb2f1f41","resolution":{"observed_at":"2026-08-08T14:06:54.735418Z","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":"2026-08-08T14:06:54.728700Z","title":"Emnist: an extension of mnist to handwritten letters,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.728700Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:b73a47f80a80911d86d5d2e2f1754c2d2b23573470b374d5c3ec910ccac5badc","observation_id":"c84ef84a-bae0-4952-b7a8-9a35af078036","resolution":{"observed_at":"2026-08-08T14:06:54.728700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.12961","last_updated":"2023-05-25T10:45:30Z","snapshot_observed_at":"2026-07-06T15:19:53.739852Z","submitted_at":"2023-04-25T16:11:10Z","title":"Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning","version":2},"cited_work":{"arxiv_id":"2304.12961","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.12961","snapshot_observed_at":"2026-08-08T14:06:54.790612Z","title":"Chameleon: Adapting to Peer Images for Planting Durable Backdoors in Federated Learning","venue":"cs.LG","work_id":"a3d7cc30-ef7e-486c-914c-f9d9e3375422","year":2023},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.740321Z"},"links":{"cited_paper":"/paper/2304.12961","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:2883489b93683013bebb422290ba012a336ac182c066e10074d53bb7d8b29cca","observation_id":"1280d9f8-267e-4640-90db-37f59a8894c9","resolution":{"observed_at":"2026-08-08T14:06:54.794989Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.12152","last_updated":"2019-09-09T08:09:25Z","snapshot_observed_at":"2026-08-08T14:51:08.356714Z","submitted_at":"2018-05-30T18:00:32Z","title":"Robustness May Be at Odds with Accuracy","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.12152","snapshot_observed_at":"2026-08-08T14:06:54.743166Z","title":"Robustness may be at odds with accuracy,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.743166Z"},"links":{"cited_paper":"/paper/1805.12152","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:6f54e604827d283da0be0432e27ded2a64bae4a21cfb7feaf77b77868b683dc0","observation_id":"e4a6229f-f15d-4e6e-b958-e416a9937429","resolution":{"observed_at":"2026-08-08T14:06:54.743166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.669112Z","title":"Tutorial on large deviations for the binomial distribution,","venue":null,"work_id":"f530516a-7771-4db1-a832-2e34879f5cce","year":1989},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.746656Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:1c9132b7b76f48051b22d363fed3bc70ca0b0825f1dd87187204b2463bbeb54e","observation_id":"2438a139-3a95-4f98-8042-6095b36d8372","resolution":{"observed_at":"2026-08-08T14:06:55.671467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10341","last_updated":"2022-06-12T16:52:52Z","snapshot_observed_at":"2026-08-04T09:45:11.538891Z","submitted_at":"2022-06-12T16:52:52Z","title":"Neurotoxin: Durable Backdoors in Federated Learning","version":1},"cited_work":{"arxiv_id":"2206.10341","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.10341","snapshot_observed_at":"2026-08-08T14:06:54.803305Z","title":"Neurotoxin: Durable Backdoors in Federated Learning","venue":"cs.CR","work_id":"52d4d653-c164-4978-b2d6-16383c415501","year":2022},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.738029Z"},"links":{"cited_paper":"/paper/2206.10341","citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:22b83f57f76a216709d8b3bc1e3a5d2d8272fa867db06b08eaca99f06dcdc44d","observation_id":"a2cacd5c-6f04-4ba5-bbe3-863618265159","resolution":{"observed_at":"2026-08-08T14:06:54.806320Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.661645Z","title":null,"venue":null,"work_id":"18c235e2-46bd-4e48-b13e-34ef21a51e43","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.750115Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:0827e3032c9c2cc8791c4562e96fc808b9ba1f3ab5a8b9e9501af787d6c84e65","observation_id":"b1673bf8-923f-4395-b175-359acee1d697","resolution":{"observed_at":"2026-08-08T14:06:55.663848Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.654475Z","title":null,"venue":null,"work_id":"d7d983cf-bdf3-4c41-8c3d-b61e94839384","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.752226Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:a4cbd1b960a3c5daeab9faea0c5741cb9985f84eaa9dac0a96a338c204093c99","observation_id":"be8cf274-1654-4861-8506-c725dc95dc7b","resolution":{"observed_at":"2026-08-08T14:06:55.657128Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.646178Z","title":"While it does evaluate the method across different batch sizes, it lacks a detailed discussion of the broader local training setup","venue":null,"work_id":"f029803d-8242-4dd4-8c2e-0f8eac34e37c","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.755006Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:6d9eb81cea064dc0c809177e015a5912c5b22dd1e0922af8b39dde7e3cd8ee80","observation_id":"5cf7798f-d248-4993-9dc9-777f8641cc2f","resolution":{"observed_at":"2026-08-08T14:06:55.648983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.638919Z","title":null,"venue":null,"work_id":"a4aa35a4-a030-4ed5-9ebc-57c39c9c17c9","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.757466Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:8df4f29d83e06af2883e79fe4e7a0986dcaa7a68944b5b1b38f7459c2712bdab","observation_id":"516ad1e5-8a27-4371-b2c9-bd32225e25d7","resolution":{"observed_at":"2026-08-08T14:06:55.641325Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.630189Z","title":null,"venue":null,"work_id":"94354a83-eae4-429b-b7f1-9f2feba17373","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.760402Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:d5cebd42eba35fa4dca92723682bb2c9ca6498fc9924f14ee2babaef79b79774","observation_id":"5bd795b7-0614-46c1-ae10-42419f3776e4","resolution":{"observed_at":"2026-08-08T14:06:55.633135Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.968581Z","title":"Available: https://api.semanticscholar","venue":null,"work_id":"34494599-4e36-491b-9e69-ca07bb3aaa00","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.598359Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:0e311d018d1a20db0994be1ccc786e4cde0ab3556bf1e1a194cb613965c54581","observation_id":"493daf92-1879-4abe-ab64-3a79df1f42ed","resolution":{"observed_at":"2026-08-08T14:06:55.970846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.910068Z","title":"Available: https://api.semanticscholar","venue":null,"work_id":"dfa574ec-d803-4ef5-8941-6ca4e38171d6","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.634805Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:d35b53acabc1adab041ce66f7bd069b77c7a868de60b9a004691f895adac49b9","observation_id":"79ff3776-b50b-4721-ac70-f2ea5a62c1f4","resolution":{"observed_at":"2026-08-08T14:06:55.912483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T14:06:55.982969Z","title":"Available: https://api.semanticscholar","venue":null,"work_id":"12c0cec6-ba6e-45b3-a579-e34361d5db48","year":null},"citing_paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T14:06:54.592124Z"},"links":{"citing_paper":"/paper/2502.07011"},"observation_digest":"sha256:7a9a429d1d87f6c43546bb2777ee296f79fbf2f2c00f3ab8ece73a81e8d1b794","observation_id":"f0295bf0-9d72-402b-bbdb-05f180709f3b","resolution":{"observed_at":"2026-08-08T14:06:55.985338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.07011","last_updated":"2025-04-28T16:24:13Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T14:52:00.228790Z","submitted_at":"2025-02-10T20:15:43Z","title":"DROP: Poison Dilution via Knowledge Distillation for Federated Learning"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":6,"verified_fuzzy":36},"total_outbound_references":67},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 1 inbound Pith citation observation for arXiv:2502.07011."}