{"as_of":"2026-08-13T10:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:550df452fb3fce3bbb68238842762693e345c565012aa2f3b29b9e7a9d81b5bc","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T19:32:26.621938Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.10673/citation-record","integrity":"/paper/2411.10673/integrity","json":"/paper/2411.10673/citation-record.json","paper":"/paper/2411.10673"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T19:32:26.404746Z","title":"Communication-efficient learning of deep networks from decentral- ized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.404746Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:1a7068e19e9e1f20f0aade541df0fd8f542dece2f357c915a6a32471ae9a0fbc","observation_id":"fd46f89f-5cd0-4ef5-a162-672ae8756868","resolution":{"observed_at":"2026-08-12T19:32:26.404746Z","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":"2026-08-12T19:32:26.410907Z","title":"Membership inference attacks against machine learning models,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.410907Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:f358066f83060f13fe7c323bcb4491a0b5d5f833a9beb43a99cbdbc48cdd456b","observation_id":"4000d4dd-4475-492e-8584-45215d5a30ca","resolution":{"observed_at":"2026-08-12T19:32:26.410907Z","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":"2026-08-12T19:32:26.416036Z","title":"Exploiting unintended feature leakage in collaborative learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.416036Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:9fc2e62a3e595a15bcc8a85e3e4d4f906f9af1fd67671385851e16c3c1596d36","observation_id":"950ab44b-fe8c-451e-af27-7514afdbc196","resolution":{"observed_at":"2026-08-12T19:32:26.416036Z","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":"2026-08-12T19:32:26.422835Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.422835Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:9eded4005de002e05e625c76b3effda0758d3b5911f070c80678fe91f26e24f0","observation_id":"0bf9e78a-6b7e-442f-83be-8349c60dd735","resolution":{"observed_at":"2026-08-12T19:32:26.422835Z","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":"2026-08-12T19:32:27.277814Z","title":"Wild patterns reloaded: A survey of machine learning security against training data poisoning,","venue":null,"work_id":"486c83bf-2e42-4fbd-8fec-d8e80892901a","year":2023},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.427728Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:1ad3ff3d272a1b03c79a0779927521383b48ec071cbf1d969c7e7cf455932410","observation_id":"b968dd4f-642a-4ee7-8c28-82caf813761a","resolution":{"observed_at":"2026-08-12T19:32:27.282771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:27.262030Z","title":"A novel data poisoning attack in federated learning based on inverted loss function,","venue":null,"work_id":"54edf476-83cf-424a-9bab-5a1e9a3e2d5f","year":2023},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.433001Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:3cfbc3388b8769f37704d682e90b60d098c2df75ccce759297774c912e88d1f6","observation_id":"62dac89c-c72d-4816-880c-a39fb2dcff24","resolution":{"observed_at":"2026-08-12T19:32:27.267562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.438975Z","title":"Local model poisoning attacks to {Byzantine-Robust} federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.438975Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:bb73273dfbbe233ecafb623576e1b710431d75544357640188790158d9d9303f","observation_id":"f5a4864d-8e92-4ede-bf16-744da77d0f7a","resolution":{"observed_at":"2026-08-12T19:32:26.438975Z","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":"2026-08-12T19:32:26.444045Z","title":"Mpaf: Model poisoning attacks to federated learning based on fake clients,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.444045Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:ef246aa5b760cf20550b0f88932256c5d01cac0133d4fa1628bad6b70299fcc2","observation_id":"0f52a96f-8fb8-45c3-95c8-a7091ed57a86","resolution":{"observed_at":"2026-08-12T19:32:26.444045Z","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":"2026-08-12T19:32:27.227743Z","title":"Backdoor attacks and defenses in federated learning: State-of-the-art, taxonomy, and future directions,","venue":null,"work_id":"240eff00-b75b-4e50-81d4-e93f6c61cdaa","year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.448652Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:249218a73c7debe6c6046424481ac5e2277a550e7dd4eab1a9258a81a4ce9313","observation_id":"ed65865a-4f78-4ebe-b36b-5ab1d6a1ff1e","resolution":{"observed_at":"2026-08-12T19:32:27.232684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.453417Z","title":"How to backdoor federated learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.453417Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:04e8295a41df2964928f0cfa63a14b63aac1b17936297afc859f524e748db454","observation_id":"9f54fb6c-b62a-42b0-8a63-77e97b93dcad","resolution":{"observed_at":"2026-08-12T19:32:26.453417Z","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":"2026-08-12T19:32:26.458591Z","title":"Manipulating the byzantine: Op- timizing model poisoning attacks and defenses for federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.458591Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:98de751e7c4d0e63f143c4fff32e579c2f21498960f1ad1908673d1f9419c217","observation_id":"c6428ebc-b91e-4c0f-9f92-6c50f878489e","resolution":{"observed_at":"2026-08-12T19:32:26.458591Z","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":"2026-08-12T19:32:26.463981Z","title":"Ma- chine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.463981Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:ded720e1d9da9b030a9b5bec92456474e6e130584ff5b8c30a7ec4790f3ce8ae","observation_id":"377e386a-671a-4e9c-8602-aa7d5109501b","resolution":{"observed_at":"2026-08-12T19:32:26.463981Z","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":"2026-08-12T19:32:26.468752Z","title":"Byzantine-robust dis- tributed learning: Towards optimal statistical rates,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.468752Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:29a3916c79bd716dea92035518677d37005a1f922070a42db3a0931fde346ad5","observation_id":"6d47eddf-3a2b-4288-b7ac-e124311cd031","resolution":{"observed_at":"2026-08-12T19:32:26.468752Z","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":"2026-08-12T19:32:27.175229Z","title":"The hidden vulnerability of dis- tributed learning in byzantium,","venue":null,"work_id":"4a026d46-d311-4028-9c50-a6d3ffe5a1aa","year":2018},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.473166Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:8c8bcc63351f3077052291ab33b9ed74119ecd6c226d5d3645039d5b0f021e28","observation_id":"9b06aaf0-d4c8-4b14-b791-19027c882fc4","resolution":{"observed_at":"2026-08-12T19:32:27.179946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:27.160522Z","title":"Auror: Defending against poisoning attacks in collaborative deep learning systems,","venue":null,"work_id":"af7ad780-7d56-49b0-b776-463f9f2f96a5","year":2016},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.477986Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:d6c9a21c8f8054b4efb3d047a8dc4e677bbd85464a747b8cfeae3ef8465fdaaf","observation_id":"64d31898-b3e7-40de-8b4a-c19fd047a614","resolution":{"observed_at":"2026-08-12T19:32:27.165403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:27.146065Z","title":"Privacy- enhanced federated learning against poisoning adversaries,","venue":null,"work_id":"394f8138-a775-44d9-8280-6154dadab45d","year":2021},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.482765Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:189487308abcf21faddba76168611bd9b824d185ab75cb4523fcafa2971f0a5e","observation_id":"37d7987c-3190-4ef2-a823-e09cd0783b67","resolution":{"observed_at":"2026-08-12T19:32:27.150692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:27.131409Z","title":"Shieldfl: Mitigating model poisoning attacks in privacy-preserving federated learning,","venue":null,"work_id":"a4a95cc8-fa5f-418a-9876-33581e79bb20","year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.487870Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:cfa14a3251eef1b13d9c9caa16de15075210c53e66ae5614a3dc8bb93af00b46","observation_id":"e8dee3ee-b34b-4649-9f8f-c6b449ddfba8","resolution":{"observed_at":"2026-08-12T19:32:27.136299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.492351Z","title":"Fltrust: Byzantine-robust federated learning via trust bootstrapping,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.492351Z"},"links":{"cited_paper":"/paper/2012.13995","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:69c102cdf9a68c2529d82f5f767a35b3e95d90f5be053bf5a13cb03d1bb49ab8","observation_id":"a615ca3d-92d7-4568-bfb4-ba15b1b8fa7e","resolution":{"observed_at":"2026-08-12T19:32:26.492351Z","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":"2026-08-12T19:32:26.497662Z","title":"Protecting federated learning from extreme model poisoning attacks via multidimensional time series anomaly detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.497662Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:39648cbf249c5e3120d313755d7435d24ad54bf0570f7c1c1b604935c9f5f952","observation_id":"38981272-d84b-473d-93c8-82225e86189b","resolution":{"observed_at":"2026-08-12T19:32:26.497662Z","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":"2026-08-12T19:32:26.503111Z","title":"Fldetector: Defending federated learning against model poisoning attacks via detecting ma- licious clients,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.503111Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:8d1b891ccb70387a241618a833339630dc7cb7b202a4fb74671a19f2e384030e","observation_id":"99643ece-0cf0-49d0-866d-2ed7a9185507","resolution":{"observed_at":"2026-08-12T19:32:26.503111Z","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":"2026-08-12T19:32:27.107733Z","title":"Deep gen- erative modelling: A comparative review of vaes, gans, normalizing flows, energy-based and autoregressive models,","venue":null,"work_id":"cb3fb104-a966-421c-8108-5b7c274d0814","year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.508106Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:ac66b1e336ab9750c0d4c6bb4a801e1920aaf6678d936ab9f1b512bd884dfebb","observation_id":"2216490a-26dd-4db4-8c5c-9bf4e52016f1","resolution":{"observed_at":"2026-08-12T19:32:27.112528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.10650","last_updated":"2021-03-16T18:33:19Z","snapshot_observed_at":"2026-08-07T10:37:36.859772Z","submitted_at":"2020-11-20T21:35:31Z","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.10650","snapshot_observed_at":"2026-08-12T19:32:26.513182Z","title":"Very deep vaes generalize autoregressive models and can outperform them on images,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.513182Z"},"links":{"cited_paper":"/paper/2011.10650","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:8629ae2f1b1731d9526cb7a9082c19158e3f6ac7c0b494b0a2e174138b284b53","observation_id":"5a3995ce-fc75-4f93-9ed0-6dc87e31b9bc","resolution":{"observed_at":"2026-08-12T19:32:26.513182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10789","last_updated":"2022-06-22T01:11:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-06-22T01:11:29Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10789","snapshot_observed_at":"2026-08-12T19:32:26.518761Z","title":"Scaling autoregressive models for content-rich text-to-image generation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.518761Z"},"links":{"cited_paper":"/paper/2206.10789","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:15d56c4a3fc1c051604a8818f8e6315224a65fbef67a4995b1aa55b1d4f1070a","observation_id":"7aa16c38-9b85-48b3-931d-f237760d2a28","resolution":{"observed_at":"2026-08-12T19:32:26.518761Z","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":"2026-08-12T19:32:27.092953Z","title":"Convergence analysis of two-layer neural net- works with relu activation,","venue":null,"work_id":"215b8c44-f74c-4639-9586-d5b031855602","year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.524462Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:c1a48a7507e0dfea6fa40e9e6b45e6d4196214082c777a895116f5e6928e3b7e","observation_id":"4e316393-7d82-4808-8b93-2865ae2b44f1","resolution":{"observed_at":"2026-08-12T19:32:27.097834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02281","last_updated":"2019-10-26T06:58:22Z","snapshot_observed_at":"2026-08-06T22:39:11.101764Z","submitted_at":"2018-10-04T15:53:32Z","title":"A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02281","snapshot_observed_at":"2026-08-12T19:32:26.529259Z","title":"A convergence analysis of gradient descent for deep linear neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.529259Z"},"links":{"cited_paper":"/paper/1810.02281","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:ecfac56a8f62193854d2a070c2fff2ceb9094bdf0a29327c414d11eb00c65df1","observation_id":"80ea4658-9103-4cbf-a321-19bfcd2c7b8c","resolution":{"observed_at":"2026-08-12T19:32:26.529259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.02189","last_updated":"2020-06-25T06:45:52Z","snapshot_observed_at":"2026-08-06T15:26:37.394053Z","submitted_at":"2019-07-04T02:04:56Z","title":"On the Convergence of FedAvg on Non-IID Data","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02189","snapshot_observed_at":"2026-08-12T19:32:26.534353Z","title":"On the convergence of fedavg on non-iid data,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.534353Z"},"links":{"cited_paper":"/paper/1907.02189","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:062ed1d4a1ed6a4dcbb522d607f17c84546bd0f951ed30dc29180a68b2ad1cfd","observation_id":"703ef0c2-a2a3-4ec5-88b7-82f4c0bd57c3","resolution":{"observed_at":"2026-08-12T19:32:26.534353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.05399","last_updated":"2022-12-11T03:39:24Z","snapshot_observed_at":"2026-07-06T14:29:08.672751Z","submitted_at":"2022-12-11T03:39:24Z","title":"Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense","version":1},"cited_work":{"arxiv_id":"2212.05399","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.05399","snapshot_observed_at":"2026-08-12T19:32:26.737506Z","title":"Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense","venue":"cs.IR","work_id":"80ab073b-5627-40b4-b910-0e889abb1a6c","year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.539893Z"},"links":{"cited_paper":"/paper/2212.05399","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:f77741a97ee3c1825085780b17bfa3a1fc77815c50942e38203916c28880b955","observation_id":"ece77aa2-5136-41a2-a4e9-8dfbeb5886f9","resolution":{"observed_at":"2026-08-12T19:32:26.742524Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-12T19:32:26.545216Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.545216Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:00b121600bd031d10e3060aa8acdc83ee4f68f2b21544b338edccfadb7bec347","observation_id":"bb9ba90f-84d5-4575-b2a6-2be95a7ea0df","resolution":{"observed_at":"2026-08-12T19:32:26.545216Z","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":"2026-08-12T19:32:27.078431Z","title":"A dual stealthy backdoor: From both spatial and frequency perspectives,","venue":null,"work_id":"04c42ca8-b372-4f16-a219-c26a8f943563","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.550120Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:f00f784266ba37366b1e39351221a68d0e492d4e6b5fa69026d90d7e33263159","observation_id":"c67ff1af-ebfb-49b2-8223-beaffc120c82","resolution":{"observed_at":"2026-08-12T19:32:27.083078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:27.063534Z","title":"Narcissus: A practical clean-label backdoor attack with limited information,","venue":null,"work_id":"3c672518-25d9-422a-8403-39c28d6fe9be","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.559981Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:eefcfd6d9108f9df88824dbf1f116b2140a1c8cda23b2c105e1373dcd398c0b5","observation_id":"4e1ef1d8-3cad-44b0-9591-4ebc0e99e795","resolution":{"observed_at":"2026-08-12T19:32:27.068253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.570434Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.570434Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:047b4927a31f8ab4a8f9c23d1e264910738ab72f3e42e8a871058661ebbad400","observation_id":"82c5fadd-c72e-4ca5-8419-1b3ed2a192cf","resolution":{"observed_at":"2026-08-12T19:32:26.570434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-12T19:32:26.574846Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.574846Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:e1d1b49ccffc341ed27c8235070b9f472a7ac6e4a4a78427f1e27c51397b2487","observation_id":"6a56b19b-2a5f-47be-a0b0-e12e9e8f0b61","resolution":{"observed_at":"2026-08-12T19:32:26.574846Z","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":"2026-08-12T19:32:26.579810Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.579810Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:a234cbf5e53fe16987f5a39327c21b20aab67ada29c303abd38bd730a7fa3618","observation_id":"9210e109-0f6d-4f08-8d0c-e6936ad82ac9","resolution":{"observed_at":"2026-08-12T19:32:26.579810Z","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":"2026-08-12T19:32:27.030313Z","title":"Baruch, G","venue":null,"work_id":"d33f6a4a-7566-4375-b476-998c0fb82f89","year":2019},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.584358Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:f53693933b1b1d4b11058a04171a9daaef1ef8debb5f7c2e6a31a9e17e7817a5","observation_id":"5144f810-9bd0-46f7-8693-d5001d3daaa0","resolution":{"observed_at":"2026-08-12T19:32:27.034633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.588707Z","title":"Adam: A method for stochastic optimization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.588707Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:9b02f591c79889b45a361072d6ef04829385691ef0cf1e041bfc77cb27b50546","observation_id":"b309e927-63f5-42e0-8a08-73ebbfe7a0da","resolution":{"observed_at":"2026-08-12T19:32:26.588707Z","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":"2026-08-12T19:32:27.006084Z","title":"A stochastic approximation method,","venue":null,"work_id":"f1a6b9ae-401a-4094-a1a1-30858b5a6c25","year":1971},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.593813Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:3f1ec5abbc58aa65fd95857b8dc711874f239b6e304db88ae4d2099d7b2481a7","observation_id":"7a1013a1-0b18-42ae-8132-104df0c4088f","resolution":{"observed_at":"2026-08-12T19:32:27.010789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.990742Z","title":"Representations of quasi-newton matrices and their use in limited memory methods,","venue":null,"work_id":"d85aabd1-d267-48e4-b752-e19d6ee1d33c","year":1994},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.598410Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:d0d20b3ecf77b7dc1998ce768cf5a90999c2baa9452698c5600181d0fa7d23ee","observation_id":"93fe62e9-0faa-4fa8-a5d5-358679bf6f3d","resolution":{"observed_at":"2026-08-12T19:32:26.995566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.972666Z","title":"Algorithm 1 Execution of VERT","venue":null,"work_id":"d6444875-c680-453e-87b3-08dd8cd0d55a","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.603014Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:d5c13f8db7c2059e0bb0dd126a34a53bc82a47d8d716a8e486d2946161a5505f","observation_id":"8bdb50d0-cb39-4e2f-9425-6975a75fe7cf","resolution":{"observed_at":"2026-08-12T19:32:26.978077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.957935Z","title":"Let the partial derivative is 0, then: ∂Φ(A; B; fpred; fproj ) ∂A = 0","venue":null,"work_id":"5c1d5ee2-1996-415e-ad32-6b3886ff4b74","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.607516Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:114afc9f266bb5f9f795d32a600e2b28fc3e07d5933c7f44c3bc899dc86bc31e","observation_id":"3eaf7cf6-f679-4596-9fb0-7f121f1dec00","resolution":{"observed_at":"2026-08-12T19:32:26.962710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.942913Z","title":null,"venue":null,"work_id":"eaf7a0b6-434c-4a2d-b9c6-41f4f493bc0e","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.612408Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:643aa61c3bf36ea54c61c52f1600f4fce5e2369d0934633650fc4e3425320659","observation_id":"67a70396-e5e2-4680-bfff-7c8bb3ce0d55","resolution":{"observed_at":"2026-08-12T19:32:26.947851Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.928566Z","title":null,"venue":null,"work_id":"8e23465e-2346-4203-b416-f4752b3d23e4","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.617296Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:28b5ee13ab05b76c3239c6bee1799738b28069929e2adc45d7cbfbea2013511b","observation_id":"f383b330-eff0-4ef7-a03f-c8e0919f215b","resolution":{"observed_at":"2026-08-12T19:32:26.933208Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T19:32:26.913538Z","title":"TABLE 4: The defense effectiveness of different defenses against large-scale model poisoning attacks in non-IID scenarios","venue":null,"work_id":"52548b85-b785-4f1c-a2c8-062cc3923690","year":null},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.621938Z"},"links":{"citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:2d60274d36b43212f19308e2abbbc5787065880e20aa5df5f5a418e8088cb42e","observation_id":"1f2d3c5a-0b5f-4c13-83d1-e7090ed548be","resolution":{"observed_at":"2026-08-12T19:32:26.918390Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.05255","last_updated":"2022-04-15T14:36:57Z","snapshot_observed_at":"2026-08-12T23:53:32.546535Z","submitted_at":"2022-04-11T16:58:04Z","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","version":2},"cited_work":{"arxiv_id":"2204.05255","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.05255","snapshot_observed_at":"2026-08-12T19:32:26.676928Z","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","venue":"cs.CR","work_id":"296961b7-ab1b-4388-a5dd-7d8fb2f83c81","year":2022},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.564657Z"},"links":{"cited_paper":"/paper/2204.05255","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:97ca0f6dd0623aeb0dd946ef17d8125c33356fa2f303e78b40fa65423c8399fc","observation_id":"4f6e31a6-6c93-445b-ac3f-73466b3cbe85","resolution":{"observed_at":"2026-08-12T19:32:26.683875Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10184","last_updated":"2023-07-03T12:28:44Z","snapshot_observed_at":"2026-08-10T13:28:20.291260Z","submitted_at":"2023-07-03T12:28:44Z","title":"A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives","version":1},"cited_work":{"arxiv_id":"2307.10184","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.10184","snapshot_observed_at":"2026-08-12T19:32:26.701276Z","title":"A Dual Stealthy Backdoor: From Both Spatial and Frequency Perspectives","venue":"cs.CR","work_id":"0c8ccd85-0770-41f3-bcd4-73340ebb1e32","year":2023},"citing_paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T19:32:26.554743Z"},"links":{"cited_paper":"/paper/2307.10184","citing_paper":"/paper/2411.10673"},"observation_digest":"sha256:b8de9fcdea3435aab999183b09673612b8726236f256cd03124dcc8bec277e1b","observation_id":"5a0fdac8-85a1-4d7e-9b1c-c58ccebc26de","resolution":{"observed_at":"2026-08-12T19:32:26.706470Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.10673","last_updated":"2024-11-16T02:25:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T19:24:17.260418Z","submitted_at":"2024-11-16T02:25:05Z","title":"How to Defend Against Large-scale Model Poisoning Attacks in Federated Learning: A Vertical Solution"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":1,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":24,"verified_exact":1,"verified_fuzzy":16},"total_outbound_references":44},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2411.10673."}