{"as_of":"2026-08-10T17:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:815640b7894a85fdb47f17ba28c32bf28a4056fc33f743c910f90f59566f0daf","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T00:45:23.424360Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T17:18:42.590627Z","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":"2026-05-17T20:10:10.952322Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"cited_work":{"arxiv_id":"2502.03801","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.03801","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Available: https://arxiv.org/abs/2502.03801","venue":null,"work_id":"86a04d6a-4ec9-47ea-8406-5d989b399f5b","year":null},"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":65,"source":"pdf_text","source_observed_at":"2026-05-17T20:08:21.578954Z"},"links":{"cited_paper":"/paper/2502.03801","citing_paper":"/paper/2511.14715"},"observation_digest":"sha256:29abc673e3b9f907a269fad8b58439b0903d4a66f1b9159e8bb40dd16a38f383","observation_id":"0fee46c0-1ac6-4e71-9109-2513216b2db3","resolution":{"observed_at":"2026-05-17T20:10:10.954312Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03801","snapshot_observed_at":"2026-07-12T17:18:42.590627Z","title":"Sok: Benchmarking poisoning attacks and defenses in federated learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.07961","last_updated":"2026-07-05T18:31:05Z","snapshot_observed_at":"2026-08-03T10:02:43.771073Z","submitted_at":"2026-05-08T16:24:54Z","title":"Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMs","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-12T17:18:42.590627Z"},"links":{"cited_paper":"/paper/2502.03801","citing_paper":"/paper/2605.07961"},"observation_digest":"sha256:376ed385f1399f17f2e118c4a4bf89d4f340cb065bc078815679810a40751535","observation_id":"88335609-46cf-4e7f-ac89-9de7938219af","resolution":{"observed_at":"2026-07-12T17:18:42.590627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.03801/citation-record","integrity":"/paper/2502.03801/integrity","json":"/paper/2502.03801/citation-record.json","paper":"/paper/2502.03801"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.492819Z","title":"Accessed: 2024-10-03","venue":null,"work_id":"65f2e666-8e08-442e-ad5e-cad3f353b9aa","year":2018},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.139580Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:24edbb3870743de97792aee7d543af0637d6df2e0f817cb954b4c8717644ddf6","observation_id":"caa862d7-3831-4790-a90d-e52bb910a1da","resolution":{"observed_at":"2026-08-09T00:45:24.497542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.477638Z","title":"Accessed: 2024-10-03","venue":null,"work_id":"736705f7-b6b5-4d60-a249-a7c2493acee8","year":2024},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.145034Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:ce644293f4927ce0936006d5072b633b0fe039fdb9723314dfb677f52752a255","observation_id":"7e2eba99-9acc-48fa-ae26-769872b2a0cb","resolution":{"observed_at":"2026-08-09T00:45:24.482622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.462078Z","title":"How to backdoor federated learning","venue":null,"work_id":"716f045f-256b-415e-8b7a-5d52775fb8a2","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.150396Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:f851e7ec94b3914ea6a35a609abe0b958c8ec507a7d22b3390054c9976555a14","observation_id":"36a72f15-83b0-4d44-85dd-9e676778c33f","resolution":{"observed_at":"2026-08-09T00:45:24.466939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.446776Z","title":"A little is enough: Circumventing defenses for distributed learning","venue":null,"work_id":"f9429914-f22f-4067-a4c8-69f6662d8e67","year":2019},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.156110Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:83274eae9dbf9138983f5ed0e0fa133d6fabdb79ca7a85cbbf03c9461a440966","observation_id":"56b6101a-93f3-4216-93bc-20719b8bbbcb","resolution":{"observed_at":"2026-08-09T00:45:24.452075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.430910Z","title":"Analyzing federated learn- ing through an adversarial lens","venue":null,"work_id":"4e19612c-1e92-4456-b9ca-86a493791fd8","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.161379Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:8227b514dfabc321cceeffdd23d8660ad47331f1f6cea31dcc8174a408b57e2b","observation_id":"267eba6f-ef9a-4814-ae57-f0b958cf1ffd","resolution":{"observed_at":"2026-08-09T00:45:24.436703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.413742Z","title":"Poi- soning attacks against support vector machines","venue":null,"work_id":"e08b1fdf-267a-4c4e-a4d7-6b10e3e2bb30","year":2012},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.166284Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:8d1cff4cde6b03c2b675e9e18e54d975fd35b8646886dc5ab1c4ad0a3ac14447","observation_id":"2e965971-e8a6-4006-8587-4a304374ec60","resolution":{"observed_at":"2026-08-09T00:45:24.418873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.398315Z","title":"Machine learning with adver- saries: Byzantine tolerant gradient descent","venue":null,"work_id":"cb7390a9-9f9f-4476-aad1-0cd47945f1cb","year":2017},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.171457Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:39f7750076b1d86c54d65718d55823c4dae4529f09d7fb848bfeb7f64999cda7","observation_id":"e43dd710-5d52-4e31-b9bf-4382161470d1","resolution":{"observed_at":"2026-08-09T00:45:24.403169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13995","last_updated":"2022-04-12T01:56:47Z","snapshot_observed_at":"2026-07-06T10:28:06.533127Z","submitted_at":"2020-12-27T18:43:39Z","title":"FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13995","snapshot_observed_at":"2026-08-09T00:45:23.177668Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.177668Z"},"links":{"cited_paper":"/paper/2012.13995","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:fd401a616f4227d5360c15979f58f04215b5496deba2175a921e855b18526c81","observation_id":"b7b81a7c-30f4-4602-904a-b29924c08e4e","resolution":{"observed_at":"2026-08-09T00:45:23.177668Z","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":"2026-08-09T00:45:24.382225Z","title":"Asynchronous byzantine machine learning (the case of sgd)","venue":null,"work_id":"512f8fe2-f772-4f85-924f-fa7a5df93905","year":2018},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.182866Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:97c0aa918df8a7b33c8a64c2a7b52e31d075972da4f75d9e15399b1f57b12fb9","observation_id":"38aae817-6d41-4c50-8385-14a304912a8f","resolution":{"observed_at":"2026-08-09T00:45:24.388075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.366396Z","title":"Utilization of fate in risk management of credit in small and micro enterprises, 2020","venue":null,"work_id":"edb4ceeb-0e06-4322-bfaf-23a7175dffcc","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.187683Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:89de300919cf79904276d9da4ae15d027cedda1caa14fbcd715c2d9509d9c8d5","observation_id":"5e891a49-be58-4e05-a592-89a43bf6f7d4","resolution":{"observed_at":"2026-08-09T00:45:24.371702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.348458Z","title":"Local model poisoning attacks to {Byzantine- Robust} federated learning","venue":null,"work_id":"eeff44f9-b5b3-4dc7-b78c-f92a201a103d","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.192220Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:463c4111c6e9e5feeaf139089801f1ca2118c3b80b9f5243ef90244cd94b3faf","observation_id":"8c2ecbe4-2ddd-49ea-9403-2e32c4d6358d","resolution":{"observed_at":"2026-08-09T00:45:24.354348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.331429Z","title":"The limitations of federated learning in sybil set- tings","venue":null,"work_id":"11508917-71f0-4d37-9494-35b7dfe71037","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.197220Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:55681829cf815ed8592b3a1836200df07825d1f6bbc618bb247fe7c3c75fbf91","observation_id":"9e59f55f-2424-4eec-bccd-06daf1ed1453","resolution":{"observed_at":"2026-08-09T00:45:24.336484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.314521Z","title":"Backdoor attacks and defenses in federated learning: State-of-the-art, taxonomy, and future direc- tions","venue":null,"work_id":"80b65cc7-7254-4fce-b12e-9c3273282638","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.201902Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:1b45732b1e5d49fc04f0b58c0a0d21540558922074351268f93a74be5b01728b","observation_id":"5c1e83ec-25c5-483c-8568-cf622de3de91","resolution":{"observed_at":"2026-08-09T00:45:24.320069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-07-06T05:56:16.413472Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-09T00:45:23.206674Z","title":"Badnets: Identifying vulnerabilities in the ma- chine learning model supply chain","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.206674Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:622c96fa7ca0d2e9680952ec64506ca330726612a29c6a4367d021269cce3cf7","observation_id":"961ec327-e2ca-48b1-8fe2-c6a6e4786e9c","resolution":{"observed_at":"2026-08-09T00:45:23.206674Z","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":"2026-08-09T00:45:24.298176Z","title":"The hidden vulnerability of distributed learning in byzantium","venue":null,"work_id":"c72d3426-fa9a-4146-992d-8055f6eccb69","year":2018},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.212053Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:6969819b781beaa2abb2aeced8a6f2a07005507a8dc9cea2bd92221760617ba0","observation_id":"9822d420-f33b-456b-a4a8-b4a0d1628b09","resolution":{"observed_at":"2026-08-09T00:45:24.302985Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.03604","last_updated":"2019-02-28T21:07:51Z","snapshot_observed_at":"2026-08-10T06:38:25.165407Z","submitted_at":"2018-11-08T18:37:03Z","title":"Federated Learning for Mobile Keyboard Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.03604","snapshot_observed_at":"2026-08-09T00:45:23.216836Z","title":"Federated learning for mobile keyboard prediction","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.216836Z"},"links":{"cited_paper":"/paper/1811.03604","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:b41ca250b5d57ec3760a9cbd5cfda1f5d2422d2d64b8398bb7d41b37fb490cb5","observation_id":"3073b29c-5ffe-4528-924c-16540e50197c","resolution":{"observed_at":"2026-08-09T00:45:23.216836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-09T00:45:23.222033Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.222033Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:f57e1d39fb9788c8726a9e637a770345a05f27eb7537c09bb2b164b21ab389b9","observation_id":"185c4deb-10a9-4dc5-8fef-668a3e5be979","resolution":{"observed_at":"2026-08-09T00:45:23.222033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-02T11:40:53.964079Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-09T00:45:23.227518Z","title":"Measuring the effects of non-identical data distribu- tion for federated visual classification","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.227518Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:e99ee7b53285fcb15a26617b4d9312b9029e57d183f3aa74479286aa0921aad2","observation_id":"52e40c0e-b6bb-444a-910d-b4b981f43e8b","resolution":{"observed_at":"2026-08-09T00:45:23.227518Z","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":"2026-08-09T00:45:24.282887Z","title":"Robust statis- tics","venue":null,"work_id":"60f01c89-1825-40e7-ae7d-4daec8db6ccf","year":2011},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.232697Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:ccdfe7ff9a5b4606e908d5af674ddfa92930fdf4329b0b0bdf31459280dde3e8","observation_id":"c247c10a-38a2-4e2a-956c-5bc6da5b9626","resolution":{"observed_at":"2026-08-09T00:45:24.287781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.266828Z","title":"Communication-efficient dis- tributed sgd with sketching","venue":null,"work_id":"bac037b3-9128-407e-b533-8cf4d6de3db3","year":2019},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.237805Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:fc7d31ba46fe3ebcd8547a86ef9ce6570adba35fee66c8aa667c735b28a684e2","observation_id":"a5e3abd7-9903-43d7-8927-7d515e8164b9","resolution":{"observed_at":"2026-08-09T00:45:24.271863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.251420Z","title":"Learning from history for byzantine robust optimiza- tion","venue":null,"work_id":"e74eec3d-cc45-4330-a55d-62d358b913c3","year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.242575Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:5c81a81aa553dd756466be5327ed7d381fe4b260d5d6a8e926a1c2656dea1f66","observation_id":"9e8cb98d-621f-4555-8efb-04612356affc","resolution":{"observed_at":"2026-08-09T00:45:24.256416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.235808Z","title":"Byzantine-robust learning on heterogeneous datasets via bucketing","venue":null,"work_id":"a83f05b7-f51d-4edc-bd46-ae20c7db061b","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.247064Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:64f1670208da4b25b6518717d5f2ac5b7b4ec56f2de4826eec13f4d16143cdc1","observation_id":"8ba39d6c-d412-4288-807d-dbd9f2aec3db","resolution":{"observed_at":"2026-08-09T00:45:24.240902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.220506Z","title":"Learning mul- tiple layers of features from tiny images","venue":null,"work_id":"ef8b733f-bb89-45e0-9255-586f4294af4c","year":2009},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.251778Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:035d2a5f0856ff58c42f5d35a0254a516de99178aa2922ea38b6cf8510068b32","observation_id":"59529125-3e64-40bb-826d-9d066d6a9529","resolution":{"observed_at":"2026-08-09T00:45:24.225421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.205501Z","title":"Ardis: a swedish historical handwritten digit dataset","venue":null,"work_id":"3e3c8338-64ea-4c1d-8349-a223ccc316d6","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.256488Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:b20f90ebfc8e335ed00abe145c5c29960c536b3469134c4dcecb3a085c7a3d3e","observation_id":"1022d868-e6e6-445e-a977-d8005e10ffd3","resolution":{"observed_at":"2026-08-09T00:45:24.210380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.190718Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":"8e5b75f1-d993-42e2-9b87-47eddc5eded5","year":1998},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.261251Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:d5f7ac148bd86a06ae1ffbc2143d798c91b07c52a947f57bf3d90d7c015fe81b","observation_id":"a3d2f7bc-44f0-4cd1-8662-e59ad64b2d75","resolution":{"observed_at":"2026-08-09T00:45:24.195636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.175354Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":"dda52a69-fba3-4c62-bbbd-bb0e6339abc1","year":1998},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.265809Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:172bcc9f7f28146088946a438c7b55a8625abf68f6d0e71661422c18ba99e346","observation_id":"6307c78a-23ac-43b9-af61-38dc186da943","resolution":{"observed_at":"2026-08-09T00:45:24.180436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.159577Z","title":"3dfed: Adaptive and extensible framework for covert backdoor attack in federated learning","venue":null,"work_id":"4329a22f-bb02-44d3-b868-be564367245a","year":2023},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.271087Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:695ed3b1c14d4ce0d4556691ff150a317697fa3633585f06517b00ed8d8a87fd","observation_id":"e57f4a53-a18b-4984-8d78-91b9471d137f","resolution":{"observed_at":"2026-08-09T00:45:24.164873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.030323Z","title":"An experimental study of byzantine-robust aggregation schemes in federated learning","venue":null,"work_id":"dadedddb-84fd-428c-9bc0-db747c0f7440","year":2023},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.276008Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:fb270c0a17642207349dcf2e3acdd3857c84ef40cd85bd0ec784126dec48648c","observation_id":"1dd5785f-4b31-4e89-8845-0a2168dbf32b","resolution":{"observed_at":"2026-08-09T00:45:24.035359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:24.015099Z","title":"Federated learning in mobile edge networks: A comprehensive survey","venue":null,"work_id":"37d8d984-72cd-4237-911a-cc73c3022d9d","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.281660Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:5549056cd9514e002634067bd64fed50347e01a89c26e4b95d5caafa6540999f","observation_id":"f70f5b96-1c09-4cc3-a297-c64c5ff39ea9","resolution":{"observed_at":"2026-08-09T00:45:24.019982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.999793Z","title":"Privacy and robustness in federated learning: Attacks and defenses","venue":null,"work_id":"55881324-d575-41ac-9a8f-59131debef9e","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.286556Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:a00c911834ae743f3e1653531fd0d2dc5fa12504cdeb77faa498b2554f7d39ae","observation_id":"ee80dd94-3fe1-4229-a18e-7564d86fd306","resolution":{"observed_at":"2026-08-09T00:45:24.005260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.984940Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"a5c6a449-84ff-4afb-b01d-1106777ffdfa","year":2017},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.290991Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:a4437960bef6c9493bd321b02b89c3a09b38f1ea7f23ddb72bac519a490a2f22","observation_id":"763670c2-c97d-42f1-a9ab-add475c8f2cd","resolution":{"observed_at":"2026-08-09T00:45:23.989796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.970046Z","title":"Feder- ated learning for internet of things: A comprehensive survey","venue":null,"work_id":"b9cf35d5-9cd0-4271-9ce1-e1bdf5b34778","year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.295550Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:5057147b86808f1631bd5ff151997f802b3dc186f553779917b784b42a32fb18","observation_id":"edba838d-347c-429d-939b-2667978e944b","resolution":{"observed_at":"2026-08-09T00:45:23.974915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.954794Z","title":"Federated learning for smart healthcare: A survey","venue":null,"work_id":"b71d3701-969e-4df0-9271-b516881515ee","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.300066Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:bff7894af3e2a96ac0de9688455c5dd631df6ce695c37015340321248fe85e02","observation_id":"17d6d000-d4cd-4b16-90f0-9d8defe2adaf","resolution":{"observed_at":"2026-08-09T00:45:23.959714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.939868Z","title":"In 31st USENIX Security Sympo- sium (USENIX Security 22) , pages 1415–1432, 2022","venue":null,"work_id":"0e9b258c-e090-42c8-9772-dce777255492","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.304529Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:addb80aa6123dcf01eb24f0ae2ea27c9189d1ea099a2898ec4e7617e7d49f8ec","observation_id":"778b39f6-2dd0-474b-a496-612dcbc96b7d","resolution":{"observed_at":"2026-08-09T00:45:23.944796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.924723Z","title":"Federated evaluation and tuning for on-device personalization: System de- sign & applications, 2022","venue":null,"work_id":"3db1492e-5ca0-481a-a066-22312b6de3de","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.309080Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:4a227034a565ac0fcec8aad19041f57fd0c1b1af0c0559cf082a7ef77a599b63","observation_id":"4d47fc2e-7ab4-419a-909f-fcdfa34f2129","resolution":{"observed_at":"2026-08-09T00:45:23.929664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.909401Z","title":"Robust aggregation for federated learning.IEEE Trans- actions on Signal Processing, 70:1142–1154, 2022","venue":null,"work_id":"c28eec87-2377-4837-9d68-de0f0777ddbb","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.313990Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:689b6d319da9f00cbba3907ebf88cef2ec26780428f351dd3a6dfcf7ec2ff7c9","observation_id":"d754262c-aec0-4b0c-a604-210812b5b944","resolution":{"observed_at":"2026-08-09T00:45:23.914333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.04329","last_updated":"2019-06-11T00:40:33Z","snapshot_observed_at":"2026-08-09T03:53:35.472619Z","submitted_at":"2019-06-11T00:40:33Z","title":"Federated Learning for Emoji Prediction in a Mobile Keyboard","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.04329","snapshot_observed_at":"2026-08-09T00:45:23.318852Z","title":"Federated learning for emoji prediction in a mobile keyboard","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.318852Z"},"links":{"cited_paper":"/paper/1906.04329","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:20dfb52c1c0ed5d207718ececa6b558719f83e0ea7c324a47fd759ad6d04c885","observation_id":"25626163-08cc-46f0-9925-3aa64b72702f","resolution":{"observed_at":"2026-08-09T00:45:23.318852Z","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":"2026-08-09T00:45:23.894448Z","title":"Reddi, Zachary Charles, Manzil Zaheer, Zachary Garrett, Keith Rush, Jakub Kone ˇcný, Sanjiv Kumar, and Hugh Brendan McMahan","venue":null,"work_id":"2c0f36a5-6393-472f-8b07-4512a1a16540","year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.324132Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:a7b9f1acf3fc934d186a88632561e0a2f4ee6158d1439e774c2ba72c762d2ecb","observation_id":"1846147c-fc7f-4da6-9fb4-7d854f82b221","resolution":{"observed_at":"2026-08-09T00:45:23.899371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.00763","last_updated":"2022-01-03T17:10:07Z","snapshot_observed_at":"2026-08-10T03:41:27.741384Z","submitted_at":"2022-01-03T17:10:07Z","title":"DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.00763","snapshot_observed_at":"2026-08-09T00:45:23.329331Z","title":"Deepsight: Mitigat- ing backdoor attacks in federated learning through deep model inspection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.329331Z"},"links":{"cited_paper":"/paper/2201.00763","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:1458b658853c01737490efcdfe9accd5959da171277fc0340161b2823cc69650","observation_id":"1c69fcd3-9674-4f44-85d3-e4cc5d7a6c72","resolution":{"observed_at":"2026-08-09T00:45:23.329331Z","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":"2026-08-09T00:45:23.879413Z","title":"Sok: Systematizing attack studies in federated learning–from sparseness to completeness","venue":null,"work_id":"22f7b91a-8581-4eb5-97d9-17585a976fb5","year":2023},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.334806Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:83c031c4440a7f9512e19749fc8271004657e08a287ef5691859405d728894d3","observation_id":"5b61a302-533e-4d1c-a8bd-caf15e701351","resolution":{"observed_at":"2026-08-09T00:45:23.884598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.864995Z","title":"Manipulating the byzantine: Optimizing model poisoning attacks and defenses for federated learning","venue":null,"work_id":"1a52dfc9-7059-4cc9-8560-da14ca75e412","year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.339726Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:732ed388a612013b477ec0a9a89efa7da5ff0cbe2a40c143196c31371a78b875","observation_id":"4ca53f48-7a24-4d29-b0d9-4fbeab2498ef","resolution":{"observed_at":"2026-08-09T00:45:23.869648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.849672Z","title":"Back to the drawing board: A critical evaluation of poisoning attacks on production federated learning","venue":null,"work_id":"d4918107-eaf5-4164-ba2f-29f36362e000","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.344548Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:8aa0a09c195f487fe01341c0885c3f8368cdf8669b74747272101f4c70466df8","observation_id":"8685fcd5-7d04-4d00-beb5-091f879d4521","resolution":{"observed_at":"2026-08-09T00:45:23.854653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.833341Z","title":"Au- ror: Defending against poisoning attacks in collabora- tive deep learning systems","venue":null,"work_id":"d22cdc37-e4ca-4488-aced-605000406e62","year":2016},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.349010Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:b62c21db8133980d05348d62d7801bc6d987421fdd451aeb30da3021168a1690","observation_id":"e25065d7-aa4e-46c2-8884-0a4d96470269","resolution":{"observed_at":"2026-08-09T00:45:23.838942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.816796Z","title":"Sparsified sgd with memory","venue":null,"work_id":"d2867ecd-3e78-4018-a9e9-74ee4fe197f2","year":2018},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.353769Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:4ba21b7baff5d89b473e4d7e16994969e00f20d7ad1b325d1d76feb6ea8ecc19","observation_id":"0c34ac9b-062c-45f2-9c6e-cb86f2a46a92","resolution":{"observed_at":"2026-08-09T00:45:23.821797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07963","last_updated":"2019-12-02T19:00:11Z","snapshot_observed_at":"2026-08-09T08:16:29.597021Z","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":"2026-08-09T00:45:23.358218Z","title":"Can you really backdoor federated learning? arXiv preprint arXiv:1911.07963,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.358218Z"},"links":{"cited_paper":"/paper/1911.07963","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:cca9fdb7b1214ccf59d325051ad248a215269b3f291a1472434dfb181ee51320","observation_id":"cf2f4e1d-4d8e-41af-b84d-94b82fc955bd","resolution":{"observed_at":"2026-08-09T00:45:23.358218Z","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":"2026-08-09T00:45:23.801974Z","title":"A compre- hensive survey on poisoning attacks and countermea- sures in machine learning","venue":null,"work_id":"f2d88733-374d-4bef-8911-ef76a8d2d247","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.363389Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:a51b7b8d3c7fa2cd101c2167d2838130d86ae020ec5d6c8e96d0301ab33a3598","observation_id":"2ee765d3-35ba-4de5-ac41-afc6f1a812f2","resolution":{"observed_at":"2026-08-09T00:45:23.806685Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.786566Z","title":"Data and model poisoning backdoor attacks on wireless federated learn- ing, and the defense mechanisms: A comprehensive survey","venue":null,"work_id":"f9f4dd86-83dc-4973-b6f0-e29142c5864b","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.367903Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:34111abb44467e6ab1b46fd103ede309bae7fe956ef1ce3432886d809cd60e8e","observation_id":"f01ffae3-68f6-4067-a955-0932d986859d","resolution":{"observed_at":"2026-08-09T00:45:23.791672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.771179Z","title":"Attack of the tails: Yes, you really can backdoor federated learn- ing","venue":null,"work_id":"84962ef8-d5fe-4c23-bd51-ca97013b94a1","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.372584Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:90ff7aec90b31f7ea023b3194216c89b556acdebe759954cc6470f0b4d582403","observation_id":"4f9409f7-923e-45f0-b74e-67c8afe3edfd","resolution":{"observed_at":"2026-08-09T00:45:23.776035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06440","last_updated":"2020-02-15T20:09:24Z","snapshot_observed_at":"2026-08-06T14:46:34.371139Z","submitted_at":"2020-02-15T20:09:24Z","title":"Federated Learning with Matched Averaging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06440","snapshot_observed_at":"2026-08-09T00:45:23.377212Z","title":"Feder- ated learning with matched averaging","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.377212Z"},"links":{"cited_paper":"/paper/2002.06440","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:19ba626dc2df335d8bf210b1ea545e02557407721521e1823310ea8ac0ec6600","observation_id":"07c1508c-06ce-4236-bc17-7b2dbef81dbe","resolution":{"observed_at":"2026-08-09T00:45:23.377212Z","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":"2026-08-09T00:45:23.756074Z","title":"Crfl: Certifiably robust federated learning against back- door attacks","venue":null,"work_id":"7cfeaeb2-9273-4c53-8645-055044730cde","year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.382127Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:79d7aa4ba49a186d5e3400499e59e0bf2a75a678699eb305c5887ec464759841","observation_id":"cc04af7f-d0cc-44ab-83b4-71ce50f18545","resolution":{"observed_at":"2026-08-09T00:45:23.761033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.740060Z","title":"Dba: Distributed backdoor attacks against federated learn- ing","venue":null,"work_id":"91a34409-da7c-4204-83a2-d789b58140b2","year":2019},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.386739Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:3b3af4b9393c1a8ba63448c489640f4e196358449b47763294e4e6e13714cb4e","observation_id":"28c1f131-35b9-4fe3-b407-c386d36b0d1a","resolution":{"observed_at":"2026-08-09T00:45:23.745465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.724122Z","title":"Fall of empires: Breaking byzantine-tolerant sgd by in- ner product manipulation","venue":null,"work_id":"9b79e811-ea49-4189-ab6c-76640a808461","year":2020},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.391546Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:f4ec9e41cd4252390eba21eefe38956f4d9635db9f436ab91f029df2c6e4188b","observation_id":"56318e87-f848-43e2-8d85-2398b31953bf","resolution":{"observed_at":"2026-08-09T00:45:23.729048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05872","last_updated":"2023-04-29T08:24:32Z","snapshot_observed_at":"2026-07-06T11:47:06.059345Z","submitted_at":"2021-09-13T11:15:15Z","title":"Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05872","snapshot_observed_at":"2026-08-09T00:45:23.396082Z","title":"Signguard: Byzantine-robust federated learn- ing through collaborative malicious gradient filtering","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.396082Z"},"links":{"cited_paper":"/paper/2109.05872","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:4c82b97febc1cd2c3f4ee1fea052c67293a9620f0e39f1d1dde4277294bdf2d6","observation_id":"f63dd423-c4c2-4e05-9e6d-2289113658a2","resolution":{"observed_at":"2026-08-09T00:45:23.396082Z","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":"2026-08-09T00:45:23.705645Z","title":"Heterogeneous federated learning: State- of-the-art and research challenges","venue":null,"work_id":"f64e756e-ab9a-4b8a-963a-9d8d549cfdc3","year":2023},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.400959Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:e1e75ceb05418ef1953a8d26510ca30bd99a24396e4366ddbe583023e9678a79","observation_id":"bcf6aa56-8a22-4bee-af21-ea2413744101","resolution":{"observed_at":"2026-08-09T00:45:23.711572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04295","last_updated":"2024-08-30T11:57:47Z","snapshot_observed_at":"2026-08-04T23:34:13.332065Z","submitted_at":"2024-07-05T06:57:30Z","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04295","snapshot_observed_at":"2026-08-09T00:45:23.405459Z","title":"Jailbreak attacks and defenses against large language models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.405459Z"},"links":{"cited_paper":"/paper/2407.04295","citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:805bf0d676041192a31682bcd129000ea4566feecff240e9d908f6bc7a49a068","observation_id":"f3ad6e4d-377b-47b0-93ea-15afba1ee3d5","resolution":{"observed_at":"2026-08-09T00:45:23.405459Z","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":"2026-08-09T00:45:23.688748Z","title":"Byzantine-robust distributed learning: Towards optimal statistical rates","venue":null,"work_id":"dea327fb-1247-4877-aefe-5a34055820c7","year":null},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.410499Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:57455de9aae043c968a49bcf175495f88b0ff5f830f7cf5f204701330b618da2","observation_id":"87e975f4-206c-4a99-8a4e-b2ba566cea8e","resolution":{"observed_at":"2026-08-09T00:45:23.693865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.673100Z","title":"Bayesian nonparametric federated learning of neural networks","venue":null,"work_id":"ed3681cd-faeb-4247-95d7-28f0e35ed8b1","year":2019},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.414894Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:b196f598dc41d1567c9ea0bef364b387f038cb010a7a59a1b0783f5353817914","observation_id":"98b4b011-f0d0-4f1c-9b7c-861a21d4c878","resolution":{"observed_at":"2026-08-09T00:45:23.678175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.656190Z","title":"Fldetector: Defending federated learn- ing against model poisoning attacks via detecting mali- cious clients","venue":null,"work_id":"aba459f7-a4e0-4d2b-8694-4c48f59251eb","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.419513Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:97963444449e5e457771ad50918e32287b1495ede97d4830711552a6f335454d","observation_id":"cf43b1bb-c255-4393-a875-73457b28d351","resolution":{"observed_at":"2026-08-09T00:45:23.662069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T00:45:23.638983Z","title":"batchrun.py","venue":null,"work_id":"54a0b9e6-954f-4d67-a681-19eba95e4e8b","year":2022},"citing_paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-09T00:45:23.424360Z"},"links":{"citing_paper":"/paper/2502.03801"},"observation_digest":"sha256:65b2022d4807ac429cca366a6a06f1db165660c912ef3f89bd553be38c92f222","observation_id":"257b4679-642d-49e3-82ba-00d7cc148a4c","resolution":{"observed_at":"2026-08-09T00:45:23.644754Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.03801","last_updated":"2025-02-06T06:05:00Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-09T03:53:53.748148Z","submitted_at":"2025-02-06T06:05:00Z","title":"SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":47},"total_outbound_references":59},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 2 inbound Pith citation observations for arXiv:2502.03801."}