{"as_of":"2026-08-10T14:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7b700eb0cc557078f29c4950ef431713aaef7cd465081405f162be584b66f8a","coverage":[{"denominator":79,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":79,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:17:47.249852Z","state":"measured"},{"denominator":79,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":79,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2506.11413/citation-record","integrity":"/paper/2506.11413/integrity","json":"/paper/2506.11413/citation-record.json","paper":"/paper/2506.11413"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:17:59.696257Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":"7169f7bb-b0c5-4fc4-a8be-892ddc4b3f57","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.194103Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:5f8ae60ab17a278d557e399cab18244724e1125c5d1782c70607959103a15c94","observation_id":"c781e0ab-169f-4ae3-ba2c-7813f2ecef6d","resolution":{"observed_at":"2026-08-07T04:17:59.700565Z","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":"2026-08-07T04:17:59.681904Z","title":"Federated learning review: Fundamen- tals, enabling technologies, and future applications,","venue":null,"work_id":"a5f4986c-5321-4566-851d-060a88367d67","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.199457Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:d555872f5aaca5bf21970f3322ffe8e4058ab61b07590b8bef87f5c6e44005d8","observation_id":"b78b8e1b-d96f-4af8-b366-8e8f7a5cc5d0","resolution":{"observed_at":"2026-08-07T04:17:59.686620Z","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":"2026-08-07T04:17:59.667803Z","title":"A survey of trustworthy federated learning: Issues, solutions, and challenges,","venue":null,"work_id":"a3cf76dd-ce76-4ce7-915f-61d682527e64","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.204555Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:f30e661a1b27e8c2e547b7ad805c9319768b3edddd71736a3ec1d046d9ca6f70","observation_id":"84a97f4b-bdf1-4651-a4a9-85d139246a10","resolution":{"observed_at":"2026-08-07T04:17:59.672672Z","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":"2026-08-07T04:17:59.653896Z","title":"Trustworthy federated learn- ing: Privacy, security, and beyond,","venue":null,"work_id":"ee992b4e-212a-4ce6-9f5a-b5cee5b069c0","year":2025},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.209787Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:0d0207b5f2310543f2c24e9bdc6708ea902dbc1e65e672689f95c0029f2f5ea5","observation_id":"607cf3b6-2e23-4111-ac94-64ef081bd124","resolution":{"observed_at":"2026-08-07T04:17:59.658056Z","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":"2026-08-07T04:17:59.640754Z","title":"Deep leakage from gra- dients,","venue":null,"work_id":"5ff1e996-b50d-483f-894d-a98d266c00b9","year":2019},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.215333Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:74b7e98192730dd39cb74cd22032a97e1e90b92e97bb82f43afccc675fbef8eb","observation_id":"be9fbfa3-5dab-4a60-acae-67248d9ee715","resolution":{"observed_at":"2026-08-07T04:17:59.644749Z","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":"2001.02610","last_updated":"2020-01-08T16:45:09Z","snapshot_observed_at":"2026-08-06T23:49:37.129499Z","submitted_at":"2020-01-08T16:45:09Z","title":"iDLG: Improved Deep Leakage from Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.02610","snapshot_observed_at":"2026-08-07T04:17:46.220200Z","title":"iDLG: Im- proved deep leakage from gradients","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.220200Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:31039a3c84490bd925b1e962682e7a950447a56fb491c01d8f9dcc623bc0f914","observation_id":"3353c9c9-5495-4978-a5f3-d677f1cea5a3","resolution":{"observed_at":"2026-08-07T04:17:46.220200Z","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":"2026-08-07T04:17:59.626360Z","title":"See through gradients: Image batch recovery via gradinversion,","venue":null,"work_id":"cd014cdf-8231-4d08-82f0-57986f45fd67","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.226049Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:57bd8c35559eb02ed73ebe2ed48d8ace01f371fd9c458ebefae3d5f50a94e689","observation_id":"51c122de-d92a-462a-bd4b-91b456a6f93e","resolution":{"observed_at":"2026-08-07T04:17:59.630834Z","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":"2026-08-07T04:17:59.544483Z","title":"SoK: On gradient leakage in federated learning,","venue":null,"work_id":"de58d920-5c13-4bdf-a1a4-4a849974e005","year":2025},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.231619Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:b13b04eb6982647fb4adb4c8c3f90136ecdef0501b7ccb7bfd38d69623a6179c","observation_id":"e412ea75-1239-4322-bb66-f918fc5c2650","resolution":{"observed_at":"2026-08-07T04:17:59.614014Z","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":"2026-08-07T04:17:59.297789Z","title":"More than enough is too much: Adaptive defenses against gradient leakage in production federated learning,","venue":null,"work_id":"7942a0cb-f370-4bdc-b30d-5c2e5ff44fba","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.236375Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:1b5708624297be0d10985ef941773225390e19792009b08bd268af1182363fc7","observation_id":"9b0efb19-7359-41d4-aa62-ed7f93434327","resolution":{"observed_at":"2026-08-07T04:17:59.417330Z","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":"2026-08-07T04:17:59.012808Z","title":"Fishing for user data in large-batch federated learning via gradient magnification,","venue":null,"work_id":"cf6e6e3e-d3a6-48c4-b64b-12a94af92b94","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.241313Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:72b10018057ef703512aa49aac35b37156affb15aaaca47675068481fa411b76","observation_id":"1a15e86d-de4a-4b67-bb41-2aa3f6ec4bbf","resolution":{"observed_at":"2026-08-07T04:17:59.127349Z","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":"2026-08-07T04:17:58.816978Z","title":"When the curious abandon honesty: Federated learning is not private,","venue":null,"work_id":"f680488f-04e3-4787-8a2a-f1feabb4ef15","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.245999Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:a661162fb33cc82242fd58237c4931c524b760e195a3e5681d243412dceeea53","observation_id":"a54ac196-3d50-465e-b9b0-889214b8be4d","resolution":{"observed_at":"2026-08-07T04:17:58.916127Z","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":"2026-08-07T04:17:58.601481Z","title":"Hiding in plain sight: Disguising data stealing attacks in federated learning,","venue":null,"work_id":"2e6c4d33-3853-462e-a336-10cf568c9bdc","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.251720Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:9943b96c78f579a847a630beeff4918ea07326bf7b48ecadbbe5c78e4b95a406","observation_id":"1c75a246-4870-4ca7-9248-5ef7caff7d08","resolution":{"observed_at":"2026-08-07T04:17:58.710174Z","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":"2026-08-07T04:17:58.473282Z","title":"Privacy and robustness in federated learning: Attacks and defenses,","venue":null,"work_id":"b38f57df-b1be-4de9-b3a5-72f3b9eb71bf","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.256794Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:56f08f8255b7aa91826c7213321493cb7e5ab720e072c336e6f47b406b3a1878","observation_id":"e02eb0aa-13bd-4001-9733-0cc645df97ad","resolution":{"observed_at":"2026-08-07T04:17:58.520896Z","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":"2026-08-07T04:17:58.338353Z","title":"Challenges and approaches for mitigating Byzantine attacks in federated learning,","venue":null,"work_id":"4d62b909-036a-4c43-b0f2-e061745931b2","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.261566Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:c5118eb09be4ff28d8e7c2e42a2339557776beba295020985c0d6f2d7959452a","observation_id":"284af255-dc86-4e6f-a4fc-b9d34b1c3d88","resolution":{"observed_at":"2026-08-07T04:17:58.401964Z","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":"2026-08-07T04:17:58.208877Z","title":"Back to the drawing board: A critical eval- uation of poisoning attacks on production federated learning,","venue":null,"work_id":"fa7f3f0e-ee21-463e-bc9b-ebe007d6976b","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.267446Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:9c9659b1183437385e168adb1de057b866b1ed91ead62d880d54f44aa91e57d2","observation_id":"fd1f8d7b-a77e-472b-a910-92e8c0fa1797","resolution":{"observed_at":"2026-08-07T04:17:58.269979Z","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":"2026-08-07T04:17:58.099959Z","title":"An experimen- tal study of Byzantine-robust aggregation schemes in federated learning,","venue":null,"work_id":"9ac00794-665f-4afb-8e31-3d99531abc0c","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.272397Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:683fe8bf21ff05cb0f151c14f2dc136535c37653c75acbecb91d0ff9302294b1","observation_id":"752ffbc9-255d-41a1-aaa8-8cd1ef2a0a56","resolution":{"observed_at":"2026-08-07T04:17:58.164620Z","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":"2026-08-07T04:17:57.910790Z","title":"Communication-efficient learn- ing of deep networks from decentralized data,","venue":null,"work_id":"acd6ccb9-dad2-45d8-93f2-eef4842142c0","year":2017},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.277368Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:4f9783251b8b3e18033eb796d7d3f923e9d19d769b4fd9341e3a1f84b4da0b67","observation_id":"085ffcc2-13f0-40f3-ae28-f103c6e82c1a","resolution":{"observed_at":"2026-08-07T04:17:57.985467Z","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":"2026-08-07T04:17:57.728670Z","title":"Machine learning with adversaries: Byzantine tolerant gradient descent,","venue":null,"work_id":"4dab551e-5db7-4f62-9063-282a49122ecb","year":2017},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.283019Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:502e07d8b1b6e19b7443f1a1401d92891d432ae518e970e14d332fbcbcde74f4","observation_id":"6f27e2b4-e8d3-4e21-a665-f03e6fb288c2","resolution":{"observed_at":"2026-08-07T04:17:57.791493Z","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":"2026-08-07T04:17:57.588733Z","title":"Byzantine-robust distributed learning: Towards opti- mal statistical rates,","venue":null,"work_id":"f29099e2-8a3c-403a-9519-ce6c18fda8b2","year":2018},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.288013Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:5bd3770f5c636a30cda48ee48dcd6d7c24c8e33dcdc76fd302ca4ede7f51ac0b","observation_id":"63d5a2e5-40d6-41b4-b9dc-6a2917996890","resolution":{"observed_at":"2026-08-07T04:17:57.636583Z","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":"2026-08-07T04:17:57.439170Z","title":"A systematic review of ho- momorphic encryption and its contributions in health- care industry,","venue":null,"work_id":"b99c8811-6d11-42f3-86c5-2706f8207765","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.293030Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:8ab0852aecdac59b8f9057f94dcb31fdcd989c5267c57f51b67c6fe80292e2cb","observation_id":"bf11e134-3a0b-4ab2-815d-d9037c98c250","resolution":{"observed_at":"2026-08-07T04:17:57.511718Z","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":"2026-08-07T04:17:57.346971Z","title":"ELSA: Secure aggregation for federated learning with ma- licious actors,","venue":null,"work_id":"9b756d6c-507e-4699-a8ea-9cea2dd50c22","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.297781Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:0b49983f5d4c2832e19383d62257c9a37552f476a4616b157db79f7f32decec5","observation_id":"f18eb849-2b01-427d-8850-6389e0809820","resolution":{"observed_at":"2026-08-07T04:17:57.374666Z","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":"2026-08-07T04:17:57.263999Z","title":"Gradient-leakage resilient federated learning,","venue":null,"work_id":"9d55aeaf-fde7-4043-b9eb-88f5f3078417","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.303264Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:d0a3cd25c15c11345bee89493837ee56f0e4c3f15f167b5e2976a3e83dfea573","observation_id":"2c3d4f34-409d-4473-abd4-da6acb3ba810","resolution":{"observed_at":"2026-08-07T04:17:57.305461Z","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":"2026-08-07T04:17:57.098898Z","title":"Does differential privacy really protect fed- erated learning from gradient leakage attacks?","venue":null,"work_id":"c043e48a-ea02-4ec0-83a8-0131d4c100e4","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.308380Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:12fb9da3249d5f2c39768207a81b2122a09e674242b45f374570ed343d6cd119","observation_id":"46b97acd-95ca-46e4-aed3-fe5d3505a525","resolution":{"observed_at":"2026-08-07T04:17:57.182495Z","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":"2026-08-07T04:17:56.950566Z","title":"Manipulating the Byzantine: Optimizing model poisoning attacks and defenses for federated learning,","venue":null,"work_id":"d15107e6-5aa9-4108-8731-cf3934a6368c","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.312927Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:be8a3d09414153ace28fad18079e624f66b8085d68b87e13e77bb29f4e247e0b","observation_id":"4b5271b5-8aa0-4057-b937-ebe6fde1f85f","resolution":{"observed_at":"2026-08-07T04:17:57.032721Z","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":"2026-08-07T04:17:56.824696Z","title":"FLTrust: Byzantine-robust federated learning via trust bootstrap- ping,","venue":null,"work_id":"d8f4c02a-91f7-4d6b-a3f9-8bc09c0519d1","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.317816Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:e0b39ad86edaa297db0491ef00999526ad158b41ea71484d3bc76ada44b0aace","observation_id":"3b70270b-efaf-4b2d-ba52-d40479f1b845","resolution":{"observed_at":"2026-08-07T04:17:56.869485Z","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":"2026-08-07T04:17:56.669125Z","title":"Byzantine-robust decentralized federated learning,","venue":null,"work_id":"22f90c22-1d5e-46fe-8f28-d79ff035c376","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.323591Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:8efd5dc9b0aab1c6a9c4386f1b7c09822925798bc9893f061f8b0530b4624cf4","observation_id":"85f19679-a210-4e66-9116-cbb2ff4398da","resolution":{"observed_at":"2026-08-07T04:17:56.754476Z","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":"2026-08-07T04:17:56.546460Z","title":"On the privacy-robustness-utility trilemma in distributed learning,","venue":null,"work_id":"135d4025-3663-41da-b8aa-17e5220b5d47","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.328269Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:9ec3213cefc7b811d58b1a4bf412e1d2a42726fbdb11ab139bde134bb17004f5","observation_id":"bd75ad2e-ceb9-4b5f-a60b-3420b45e2475","resolution":{"observed_at":"2026-08-07T04:17:56.614889Z","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":"2026-08-07T04:17:56.421973Z","title":"Fed- erated learning: Challenges, methods, and future di- rections,","venue":null,"work_id":"a020e682-ed46-40b6-9c91-1df9e3945ae7","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.333197Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:bb832a1bba7c8a39ae527337ef2d72b20f3da92506d4b9e3d61082329ce38b54","observation_id":"70b508cd-c579-483f-b770-b77fc7e725b2","resolution":{"observed_at":"2026-08-07T04:17:56.503857Z","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":"2026-08-07T04:17:56.251266Z","title":"Inverting gradients – How easy is it to break privacy in federated learning?","venue":null,"work_id":"c71a21aa-1c3b-4ec0-90a7-3263df7bc4e2","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.338728Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:28d81e263ac4820c74b547dda51c6cbc77c9b92e4d8004ea72335850f755ef20","observation_id":"f0c43998-6ed1-4a63-b395-da2e5438ecf9","resolution":{"observed_at":"2026-08-07T04:17:56.333755Z","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":"2026-08-07T04:17:56.072229Z","title":"Truth serum: Poisoning machine learning models to reveal their secrets,","venue":null,"work_id":"e67d346e-804d-4ddb-9d47-c7b53d4aae09","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.343329Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:57fc8a32d41b7e95d55a156138c3d7d56b703dcc3f50786275c27cc9fafd4f03","observation_id":"7d24b99c-b46f-49da-8c7e-137eefdb6f24","resolution":{"observed_at":"2026-08-07T04:17:56.140348Z","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":"2026-08-07T04:17:55.788643Z","title":"Membership inference attacks against machine learn- ing models,","venue":null,"work_id":"04de97c2-b3dc-4dca-940c-1b6e217d7083","year":2017},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.348348Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:c473e2a717e7e468bd0c4e5044e3f3eda3ebf5073ef9346d983628d6f351fc98","observation_id":"ff404445-1c0c-440d-9f1b-4f4474fcb050","resolution":{"observed_at":"2026-08-07T04:17:55.946927Z","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":"2026-08-07T04:17:55.486875Z","title":"Membership inference attacks and defenses in fed- erated learning: A survey,","venue":null,"work_id":"8cd5fa96-3576-49db-a0f7-9b65c265a868","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.353186Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:3b3d9933e231be230e8a040264d756c4d678a268d240b7601ec285fe1d300a3b","observation_id":"e794b154-da16-447f-9163-5c2cc062b6c2","resolution":{"observed_at":"2026-08-07T04:17:55.641881Z","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":"2026-08-07T04:17:55.276388Z","title":"Compre- hensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning,","venue":null,"work_id":"0fa7f438-8fc7-4b90-b85d-e64b0e1774b1","year":2019},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.357893Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:962ba6deeae100782e55f7c3b000a8fd556f6bd63b8d1be896aa2e6092cc57e5","observation_id":"e9b2dda2-d206-4157-b754-86a2f334280c","resolution":{"observed_at":"2026-08-07T04:17:55.371027Z","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":"2026-08-07T04:17:55.047554Z","title":"Exploiting unintended feature leakage in collaborative learning,","venue":null,"work_id":"eef863c0-1ea4-4d49-8cba-b3fb66fc94ad","year":2019},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.362614Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:5fa05392374bb1cd1b5587627c1e6ffa0779711afe75d0bcf187eae8cd9b0637","observation_id":"d83ba20c-bbb9-4af7-8540-ad9f87598fbe","resolution":{"observed_at":"2026-08-07T04:17:55.162395Z","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":"2026-08-07T04:17:54.734245Z","title":"Deep models under the GAN: Information leakage from collabora- tive deep learning,","venue":null,"work_id":"6929dceb-aa94-4740-b926-40555af7f6b0","year":2017},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.367836Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:dce3f8a6513b344c243fc9a39f9d33eda5e888be9960ac55fc5caa92eff6c5a7","observation_id":"f34e244c-ee6e-48d7-aaf8-631f516aeca6","resolution":{"observed_at":"2026-08-07T04:17:54.889761Z","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":"2026-08-07T04:17:54.422894Z","title":"FedInverse: Evaluating privacy leak- age in federated learning,","venue":null,"work_id":"eb2445df-c768-4a1e-a35e-22582e609a58","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.372723Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:cef8d21f9530031d6808a37152cac73bc70c5f33dd9fbba54baba595720213d3","observation_id":"af389030-0eb7-4e70-a2b4-313a140343c3","resolution":{"observed_at":"2026-08-07T04:17:54.574162Z","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":"2026-08-07T04:17:54.183405Z","title":"Rethinking privacy preserving deep learning: How to evaluate and thwart privacy attacks,","venue":null,"work_id":"b9fee969-1529-4a55-8243-03fd603bf70b","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.377442Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:650370652444556abe87fa1bd8c5b316ae889206ac3543ff4c490f8074ab29ea","observation_id":"783fe47e-28dd-4a88-8cbb-85ff4b1deccb","resolution":{"observed_at":"2026-08-07T04:17:54.296033Z","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":"2026-08-07T04:17:53.988897Z","title":"The resource problem of using linear layer leakage attack in federated learn- ing,","venue":null,"work_id":"9a92646a-d1e0-44f2-b05c-8ad6fd8644c8","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.385285Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:23a669d7f402636dcc34892c1c93d892e6d83555f8d1903a4fd66de133e373ef","observation_id":"e4508eb4-cf9b-478e-9fa0-ddfc1dc4950b","resolution":{"observed_at":"2026-08-07T04:17:54.068145Z","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":"2026-08-07T04:17:53.805554Z","title":"FedSecurity: A benchmark for attacks and defenses in federated learning and federated LLMs,","venue":null,"work_id":"381a54de-e65e-494e-bb92-897edc33bde1","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.393056Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:26530519366e8b9f0ccc5a6b1e855756b2de24872aa163225d26ccf219e7fc58","observation_id":"8673d94a-7f52-4129-8de7-5f47b47002a5","resolution":{"observed_at":"2026-08-07T04:17:53.873055Z","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":"2026-08-07T04:17:53.624750Z","title":"Fall of empires: Breaking byzantine-tolerant SGD by inner product ma- nipulation,","venue":null,"work_id":"9a5e19e6-f85e-4bbf-8177-bc612dbe1c53","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.400584Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:fa8fb4d9ba08b854dd3d0d03c65e2b9d553e8593bc2308fad9b77522a877aae8","observation_id":"dc9b02cb-5942-491b-987b-d7d6d4ef0722","resolution":{"observed_at":"2026-08-07T04:17:53.712490Z","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":"2026-08-07T04:17:53.434579Z","title":"3dFed: Adaptive and extensible framework for covert backdoor attack in federated learning,","venue":null,"work_id":"0201c9f8-6af9-48de-a4b2-d2d404dbec17","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.412294Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:5654c9877243b9f1fe49be2a48b4f710baeec8c6c3fdbad6f84fe1c1984ac35f","observation_id":"68b29ff4-e92f-48b7-99ef-94bb50b752bf","resolution":{"observed_at":"2026-08-07T04:17:53.510009Z","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":"2026-08-07T04:17:53.318527Z","title":"Data and model poisoning backdoor attacks on wireless federated learning, and the defense mecha- nisms: A comprehensive survey,","venue":null,"work_id":"557a3a28-06b9-4473-987a-24156827d654","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.419535Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:9db39321f6959c88977f5ec078153fedda617f2d26f4b8dd1af1e9ed405bd097","observation_id":"fe756282-dd90-47d1-805b-a8cc386b1905","resolution":{"observed_at":"2026-08-07T04:17:53.349711Z","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":"2026-08-07T04:17:53.129523Z","title":"Byzantines can also learn from history: Fall of cen- tered clipping in federated learning,","venue":null,"work_id":"797b8dab-df8a-443d-a613-cc1cc94bf12a","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.427970Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:c0698e278c2d5b0b4bb9bad3a8b620ebcd1b361015cc4f7b8ca0e2058e5ac1e9","observation_id":"63cdd97b-d8c8-4e0b-8ff2-168a2d85bf4e","resolution":{"observed_at":"2026-08-07T04:17:53.231705Z","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":"2026-08-07T04:17:52.990100Z","title":"AgrEvader: Poisoning membership inference against Byzantine-robust federated learning,","venue":null,"work_id":"5c265ee1-2111-4064-ade2-b56d2cc42db3","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.436679Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:19af1eec52e57ef11deeb5db8bc244956926ccb71a3c21f519576142deeb8f35","observation_id":"c8af39fc-5e88-4d80-868b-685e87548599","resolution":{"observed_at":"2026-08-07T04:17:53.019840Z","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":"2026-08-07T04:17:52.834818Z","title":"Loden: Making every client in federated learning a defender against the poisoning membership inference attacks,","venue":null,"work_id":"bdf7afae-02a1-4ab5-9977-f999dd974ae7","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.446882Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:6d06db5a38ddcab2225326523162660f3f6a33d7ef3a1d121e5411671d2509e1","observation_id":"6bad38e7-853a-4f1b-9c8c-9b7d4ba24f26","resolution":{"observed_at":"2026-08-07T04:17:52.906415Z","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":"2026-08-07T04:17:52.674190Z","title":"Understanding clipping for federated learning: Con- vergence and client-level differential privacy,","venue":null,"work_id":"0333d4a5-99b8-47a5-b89b-8a10c16e14e4","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.456844Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:2c03c37d111c457a16dee73848759f3417805c21c81ac5f39cfaa8a66c4a1ef0","observation_id":"270bd0fb-5d38-4f40-8bd6-9e40f45efb15","resolution":{"observed_at":"2026-08-07T04:17:52.731694Z","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":"2026-08-07T04:17:52.478578Z","title":"Deep learning with differential privacy,","venue":null,"work_id":"8f4b547e-ffc5-47bd-a328-5e02d68d29ff","year":2016},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.466704Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:bf2b0dffeb35c2ccd74fa7bc9d1c9cbe71b9537ad678354eaaa444ebcd5b4513","observation_id":"d6b09afb-fb39-4331-b041-59bf89352088","resolution":{"observed_at":"2026-08-07T04:17:52.580245Z","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":"2026-08-07T04:17:52.333167Z","title":"User-level privacy-preserving feder- ated learning: Analysis and performance optimization,","venue":null,"work_id":"b1526580-ce30-4afd-8c4f-2910b256469c","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.477973Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:2c70d925b1c33cf7a5713f9dedba6a5054bdb06606a5e5f75cb008cdf39e3c45","observation_id":"ad9adfc5-4626-47be-a859-c5acde89d021","resolution":{"observed_at":"2026-08-07T04:17:52.394575Z","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":"2026-08-07T04:17:52.165724Z","title":"Federated latent dirich- let allocation: A local differential privacy based frame- work,","venue":null,"work_id":"9b291426-aa38-4c98-8884-b0c25b0f3632","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.489760Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:a14c7873ed009dd19c0a5730ff9118c6a89b940461e1265279019e1e7158ae4c","observation_id":"c24e8e41-b75f-48f2-89cf-8f40f671126e","resolution":{"observed_at":"2026-08-07T04:17:52.241157Z","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":"2026-08-07T04:17:51.980682Z","title":"The distributed discrete gaussian mechanism for federated learning with secure aggregation,","venue":null,"work_id":"da7d8168-5a20-4981-840e-992476aee929","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.502143Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:cec250a402340dbb137034819080370a29f765ebad0ac64d9f0a805478ca689f","observation_id":"c28f3676-59e5-416e-afa0-93029f912b41","resolution":{"observed_at":"2026-08-07T04:17:52.075749Z","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":"2026-08-07T04:17:51.787711Z","title":"Differentially-private fed- erated linear bandits,","venue":null,"work_id":"a49cb052-cc88-4be8-adbf-93c578766788","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.513628Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:42a122f07e36dab7fecb3fda0c7a3d209cd102b065b546f29a97488b115dcad6","observation_id":"dbf17113-00eb-44e1-8a7b-f0261c9bc633","resolution":{"observed_at":"2026-08-07T04:17:51.895453Z","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":"2026-08-07T04:17:51.635608Z","title":"Practical secure aggregation for federated learning on user-held data,","venue":null,"work_id":"b6d1874e-6bee-44f1-a5d0-1fe22f8c8c2e","year":2016},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.525976Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:3f172af4c50b25c7ad088956937a87da875d7e62defc0497ad067e3012d0aa01","observation_id":"c93fae99-7d77-44b2-9e2f-d2a733cde1dd","resolution":{"observed_at":"2026-08-07T04:17:51.716643Z","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":"2026-08-07T04:17:51.498017Z","title":"A survey on federated learning: A perspective from multi-party computation,","venue":null,"work_id":"d923ddc8-5dda-4d21-a239-a2060faad260","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.535805Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:90a2342734faabe4acd0c66ef41df23ebd134673b47bfb391aff3832eb249443","observation_id":"0f33741c-6ad4-41e5-ba22-e32556731233","resolution":{"observed_at":"2026-08-07T04:17:51.561816Z","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":"2026-08-07T04:17:51.250986Z","title":"Secure federated learning with fully ho- momorphic encryption for iot communications,","venue":null,"work_id":"de6f4069-747b-4ad7-a431-22c9661e0aa7","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.548852Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:8116ea6f8dad693d131f6518f439ad5e76795df55f378150d5a4a92c1376d367","observation_id":"3b6490e7-d6ea-4bb2-8eba-33b72839b2f0","resolution":{"observed_at":"2026-08-07T04:17:51.374675Z","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":"2026-08-07T04:17:51.078793Z","title":"Blockchain-based federated learning with secure aggregation in trusted execution environment for internet-of-things,","venue":null,"work_id":"1bbc6e0b-7aa1-4f5d-b629-fe26f8032cce","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.560684Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:0074e7478c06670e97a526608ff7997c03d90f40ccf51f6dc94d8d37ad5ec882","observation_id":"dd62adbc-d395-4977-9a14-341d3fdee0ad","resolution":{"observed_at":"2026-08-07T04:17:51.178537Z","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":"2026-08-07T04:17:50.921326Z","title":"MESAS: Poisoning defense for federated learning resilient against adaptive attackers,","venue":null,"work_id":"124c89e4-79ac-447f-ac5b-3dd2add5f7c1","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.572610Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:4f3ee0e54a3905ad3ab405d3c71054df51ff57cbb4ec04ec30cfb3a0eb8be2d8","observation_id":"c891c439-1cff-4368-9fb9-35c96f2d577f","resolution":{"observed_at":"2026-08-07T04:17:51.004232Z","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":"2026-08-07T04:17:50.748177Z","title":"FreqFed: A frequency analysis- based approach for mitigating poisoning attacks in federated learning,","venue":null,"work_id":"8e447d41-1d56-453e-adaa-44404cd6bf1d","year":2024},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.582595Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:80e22e8b6bd1fd5bf8576252450783d877ba68bb1f7716f4ec4600d784e54790","observation_id":"7f3ecbdf-7456-4164-ac32-06c5c42d5e55","resolution":{"observed_at":"2026-08-07T04:17:50.861791Z","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":"2026-08-07T04:17:50.565429Z","title":"Byzantine- robust federated learning through collaborative mali- cious gradient filtering,","venue":null,"work_id":"99a435a4-9514-4f69-aec2-8fc10d9a48a7","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.595261Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:dc7b855513151cd706de2ff55e126c39bf99733e6bf81b168979e1faa28da004","observation_id":"f02387a9-a645-4e3c-949d-25e1843c30a3","resolution":{"observed_at":"2026-08-07T04:17:50.660257Z","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":"2026-08-07T04:17:50.388356Z","title":"Differential privacy,","venue":null,"work_id":"d5bf8f0a-a645-4cb2-9526-e3d33d99e734","year":2006},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.609203Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:1b26ef1902985cef3e8d3416dcce89f6b8879804f257a3eefa15a514450d51ea","observation_id":"6bb96b86-690b-4298-bb17-fdfb54239f4c","resolution":{"observed_at":"2026-08-07T04:17:50.469933Z","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":"2026-08-07T04:17:50.205982Z","title":"Differential privacy meets federated learning under communication constraints,","venue":null,"work_id":"b40ee360-7366-4e66-9aa0-87b7a297e487","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.625615Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:189a5b0c38ba4a7092475f118a2bdbe7841ef9384819f8430da67e7d8d48c53f","observation_id":"a5a6a13c-e126-4435-a0c9-5399949fd516","resolution":{"observed_at":"2026-08-07T04:17:50.272327Z","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":"2026-08-07T04:17:50.022172Z","title":"Local SGD converges fast and communi- cates little,","venue":null,"work_id":"c5a4f5b9-d907-4f2a-b683-4dad5867a526","year":2019},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.639010Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:cb4f412e8d32c771b87dde4b840f28411c5707f719ca270660ebefb007c8e3b7","observation_id":"4b44f833-0ea3-4cbd-bb34-d7e75bbbf11b","resolution":{"observed_at":"2026-08-07T04:17:50.089467Z","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":"2026-08-07T04:17:49.906185Z","title":"FL-NTK: A neural tangent kernel-based framework for federated learning analysis,","venue":null,"work_id":"cab0d7c2-fa2b-49e8-9726-ed3bca02aff9","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.652325Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:e8bf0fe0638723c2410a9dd13037ed4f7bde95f15453cb9775cda0b4e0b27767","observation_id":"6f98315f-4661-4513-99a3-131898c5d54f","resolution":{"observed_at":"2026-08-07T04:17:49.969532Z","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":"2026-08-07T04:17:49.706033Z","title":"Recon- structing individual data points in federated learning hardened with differential privacy and secure aggrega- tion,","venue":null,"work_id":"52c56eef-93f1-4cfa-9ef2-c979bb1d5cb7","year":2023},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.668244Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:7c6560e074275173510e17760106d2491ad874c29cde0873f29614f7747cdcd3","observation_id":"b5784925-56b1-444f-807e-648a9ec331c0","resolution":{"observed_at":"2026-08-07T04:17:49.810769Z","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":"2026-08-07T04:17:49.526597Z","title":"Understanding gradient clipping in private SGD: A geometric per- spective,","venue":null,"work_id":"820bdd7c-aa63-4751-b304-06297c4ce294","year":2020},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.684206Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:81a5a9268ba0178944c78bbed45fbba6c7631da3ea4ff886c4ae6fb4cfc9400b","observation_id":"e85eb1b0-2660-456f-97a9-3d73b7e41400","resolution":{"observed_at":"2026-08-07T04:17:49.593683Z","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":"2026-08-07T04:17:49.283069Z","title":"Autoencoders, unsupervised learning, and deep architectures,","venue":null,"work_id":"9b4efdf6-765f-47dc-9c76-a94a88786759","year":2012},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.700235Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:055bcd68cebe552b71f8ab9bef68a1ef12151d00fab8859b6630d1328c29e9d7","observation_id":"09c13e6e-01d7-4f81-ba16-b647fc9bfe1c","resolution":{"observed_at":"2026-08-07T04:17:49.376011Z","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":"2026-08-07T04:17:49.078553Z","title":"Robustness of graph neural networks at scale,","venue":null,"work_id":"c359d6c7-c781-4228-b0b5-1c63dee94f4a","year":2021},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.716881Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:4f660b4bafa0204e1cf7f19c8367a797c95b95eb14fe5fd34998ad197c739c49","observation_id":"e8d49b20-0fe1-4d7c-8e8e-23249c052538","resolution":{"observed_at":"2026-08-07T04:17:49.165165Z","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":"2026-08-07T04:17:48.847358Z","title":"RSA: Byzantine-robust stochastic aggrega- tion methods for distributed learning from heteroge- neous datasets,","venue":null,"work_id":"b55785d6-3646-4024-bd8c-95acef8b5c26","year":2019},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.735708Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:e3184112aeefba5a94e5855751b2a8c55563a5011345bf2a6673f1ff802f3a02","observation_id":"df9fe45b-f9cc-44ba-9169-58bb36d53232","resolution":{"observed_at":"2026-08-07T04:17:48.913107Z","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":"2026-08-07T04:17:48.621802Z","title":"Neurotoxin: Durable backdoors in federated learning,","venue":null,"work_id":"12939cab-d61b-44f0-81f0-5de34ff26f15","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.749346Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:6a2bee5a38c3b8775e05869124473c18438a1cf953d9a41dc25c5cf575536f03","observation_id":"c36e54a2-6790-40e7-b707-59d8b38f9636","resolution":{"observed_at":"2026-08-07T04:17:48.759225Z","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":"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":"2026-08-07T04:17:46.763483Z","title":"Measur- ing the effects of non-identical data distribution for federated visual classification,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.763483Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:d4bab65dd7fa325e0f0a0afbb799a9edf580394a4ceb377d478cf0e570ca92c7","observation_id":"9f4b5d07-f640-4049-87fd-0f2c9baaeb04","resolution":{"observed_at":"2026-08-07T04:17:46.763483Z","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":"2026-08-07T04:17:48.395597Z","title":"Gaussian differen- tial privacy,","venue":null,"work_id":"8b7a2adc-fd4d-4497-a0c8-1eccdc5a8a1d","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.781546Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:4dfe318df4853a2e457c8c054de94ca8f5a164198348c00f4bb6980862e4245f","observation_id":"0d112c86-658b-4fcd-a93a-57ffea1aba5b","resolution":{"observed_at":"2026-08-07T04:17:48.482941Z","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":"2002.10940","last_updated":"2021-09-27T21:16:21Z","snapshot_observed_at":"2026-08-09T16:30:02.185904Z","submitted_at":"2020-02-25T15:12:15Z","title":"Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.10940","snapshot_observed_at":"2026-08-07T04:17:46.792095Z","title":"Stochastic-sign SGD for federated learning with the- oretical guarantees,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.792095Z"},"links":{"cited_paper":"/paper/2002.10940","citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:424595434ba2c67e53f0818a085c9af013ab505898404301174aa500b0227400","observation_id":"e443549c-b651-4ca3-9450-c1c3f949e365","resolution":{"observed_at":"2026-08-07T04:17:46.792095Z","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":"2026-08-07T04:17:48.193984Z","title":"Communication-efficient and Byzantine-robust differentially private federated learning,","venue":null,"work_id":"5fe38f67-b756-472c-8683-5201233ce2e1","year":2022},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.852010Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:b13d9c6a35d12b8289e935c28ed5c10160f4e8a34f834f26ac58d3930b599979","observation_id":"7ac5ffee-13df-4699-b66c-6440c551b5f9","resolution":{"observed_at":"2026-08-07T04:17:48.296775Z","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":"2026-08-07T04:17:48.076637Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,","venue":null,"work_id":"4af1bd89-5931-44ea-b2ba-29ca85a43261","year":2015},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.899383Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:bbd768fa93f0cdb1a5c0039dc77489bcb225e5ef0907a2c9112af6ff53077148","observation_id":"359de96d-e7e4-48a2-af0c-f5f483d291c3","resolution":{"observed_at":"2026-08-07T04:17:48.115263Z","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":"2026-08-07T04:17:47.927528Z","title":"Efficient backprop,","venue":null,"work_id":"6c584234-1506-46ab-82a5-1fc0bfee924c","year":2002},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:46.967611Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:46daa34f1cc4c57cf19ae527edd72fd8f8b58d09152644cc50babb74769502d4","observation_id":"027fbca9-5622-42e9-88ad-712b4bb2b4ac","resolution":{"observed_at":"2026-08-07T04:17:47.986716Z","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":"1312.6120","last_updated":"2014-02-19T17:26:57Z","snapshot_observed_at":"2026-08-08T04:46:43.735461Z","submitted_at":"2013-12-20T20:24:00Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6120","snapshot_observed_at":"2026-08-07T04:17:47.031882Z","title":"Ex- act solutions to the nonlinear dynamics of learn- ing in deep linear neural networks,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:47.031882Z"},"links":{"cited_paper":"/paper/1312.6120","citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:26054831bd7b55ec357d7cb005b81e4d9b543894e3ed89d63c478e46279433b8","observation_id":"b46df620-d8d1-40e7-811d-e224aa855732","resolution":{"observed_at":"2026-08-07T04:17:47.031882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-07T04:17:47.095680Z","title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:47.095680Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:aabf2de94cab0c97cb1e4702560bda5f31507cc14b72fddf48538a1ace254ca2","observation_id":"15fb298a-3805-452d-9845-774e3bfbdee2","resolution":{"observed_at":"2026-08-07T04:17:47.095680Z","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":"2026-08-07T04:17:47.748446Z","title":"The MNIST database of handwritten digit images for machine learning research [best of the web],","venue":null,"work_id":"caf9e595-04f7-44c6-be56-b241d23ca400","year":2012},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:47.138576Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:b8fe1c1d0c4c480e4dcb5acfebf3121569380848fa9cd44b5c592ee612fb8d19","observation_id":"ca5f2399-bf57-4507-ac23-d2b2784340f5","resolution":{"observed_at":"2026-08-07T04:17:47.812449Z","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":"2026-08-07T04:17:47.602284Z","title":"CNN for handwritten Arabic digits recognition based on LeNet- 5,","venue":null,"work_id":"b25ccc72-2c60-4ecd-855c-b69ddf84c889","year":2016},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:47.205901Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:d05c14e24be2229c6e739c09a3f2f42f7719f59fae4522da86f51d90cce34923","observation_id":"3e5c5a32-9350-4aea-9ee2-56a085c2b25f","resolution":{"observed_at":"2026-08-07T04:17:47.670469Z","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":"2026-08-07T04:17:47.423991Z","title":null,"venue":null,"work_id":"1b143564-cf97-487c-8975-5db68777a398","year":null},"citing_paper":{"arxiv_id":"2506.11413","last_updated":"2025-06-13T02:23:41Z","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T04:17:47.249852Z"},"links":{"citing_paper":"/paper/2506.11413"},"observation_digest":"sha256:f3a5d59634cae20e2ac7292d1d44404aac69a5b83ce8bd90c26090c6656942df","observation_id":"918cfff6-3acf-40be-b9cd-146e28f923f5","resolution":{"observed_at":"2026-08-07T04:17:47.510122Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2506.11413","last_updated":"2025-06-13T02:23:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T00:58:55.513764Z","submitted_at":"2025-06-13T02:23:41Z","title":"Byzantine Outside, Curious Inside: Reconstructing Data Through Malicious Updates"},"reference_resolution":{"displayed":79,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":73},"total_outbound_references":79},"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 79 of 79 outbound references and 0 inbound Pith citation observations for arXiv:2506.11413."}