{"as_of":"2026-08-10T03:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b88530246b68e02929a3b33110157cfbd9aea16e3aa0806fe8269bcc0c6243f","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:21:07.900685Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2506.08435/citation-record","integrity":"/paper/2506.08435/integrity","json":"/paper/2506.08435/citation-record.json","paper":"/paper/2506.08435"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:21:09.926923Z","title":"Federated learning and differential privacy for medical image analysis.Scientific reports, 12(1):1953, 2022","venue":null,"work_id":"f7ca03f9-a26a-45ec-b13a-1cfa5d0cb3a6","year":1953},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.371907Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:cf11f6ab56d4543050387e04c932e9f10c67b54cafddb03b9b059a567bdfae8e","observation_id":"132b2831-d662-49c8-8aea-3bbea1293836","resolution":{"observed_at":"2026-08-07T05:21:09.934491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.898644Z","title":"A hybrid frame- work for glaucoma detection through federated machine learning and deep learning models.BMC Medical Infor- matics and Decision Making, 24(1):115, 2024","venue":null,"work_id":"a1801ea2-8348-436c-8053-650f917df3cf","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.381277Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:4e92d9d117dc4bee84ee53057789c89ad98f3c82650942829a38df94f4414a3b","observation_id":"824d0520-0c73-45d6-ad7c-cffb769670ae","resolution":{"observed_at":"2026-08-07T05:21:09.906410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.870706Z","title":"Privacy-preserving deep learning via additively homo- morphic encryption.IEEE TIFS, 13(5):1333–1345, 2017","venue":null,"work_id":"5a2c980a-750e-4c72-bf04-b4acfe1aaa32","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.393144Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:64295f60546b404deb7ff4c7708a78ad67d2f69b5209e7878491f4989f4a17a8","observation_id":"9a94d7ca-f6c6-488b-a9fb-94c89d0308fb","resolution":{"observed_at":"2026-08-07T05:21:09.877193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.835299Z","title":null,"venue":null,"work_id":"028d5f8a-5b46-4c0a-9817-e80b43458fbe","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.401321Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:90fdb59cbd12f2c78b62dbacac7cd4bdd72e1e9f0aa2a15690f64d18767ba784","observation_id":"bf8d38bc-02d4-47c7-8999-752720ab3017","resolution":{"observed_at":"2026-08-07T05:21:09.841885Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.811307Z","title":"Bartoldson, James Diffenderfer, Konstantinos Parasyris, and Bhavya Kailkhura","venue":null,"work_id":"b2564ad8-2e61-4c18-b29d-6e6789813666","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.408854Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0eefb37dc4ef61d3921fbc343b1093e76ee68cc21f3d82b9242e79cb0836e18b","observation_id":"85895d3e-c025-4c54-849b-e914a89d16cc","resolution":{"observed_at":"2026-08-07T05:21:09.819918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.790274Z","title":"When the curious abandon honesty: Federated learning is not private","venue":null,"work_id":"486d7e60-0967-40aa-bd64-cf7b45681e61","year":null},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.416324Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ae822e79134d4c1089df27abba2fa621680554570472e068a4a5287c40b5b4a9","observation_id":"8ae3038c-a7cd-4acf-8c2e-f1b66820a216","resolution":{"observed_at":"2026-08-07T05:21:09.796724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.739505Z","title":"Practical secure aggregation for privacy-preserving ma- chine learning","venue":null,"work_id":"1c6817e8-3bdc-4cc9-94fb-65b98e71177f","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.425802Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:f27843e348b310a85e3a5d9573b45b98c1ccd8bff120223c8d7c068dc399a315","observation_id":"51f59b5c-3a14-4852-b9d2-4dc32e4350ec","resolution":{"observed_at":"2026-08-07T05:21:09.756324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.715587Z","title":"Convex optimization.Cambridge UP, 2004","venue":null,"work_id":"41d1ac11-8a5f-4cb9-89c1-524ef67f2e2a","year":2004},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.439000Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:447d58d3166068e152c82ad184d26bf4f8147e90622bd8d9fe95548b3bafebf5","observation_id":"21ad8c8e-14c2-4cf3-928b-4af29517ab7a","resolution":{"observed_at":"2026-08-07T05:21:09.721501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.677201Z","title":"Extracting training data from large language models","venue":null,"work_id":"d3c99953-911b-418f-83da-30c3bf664af4","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.445224Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ec4e5eac6aa83d955b803fcb87ccb10b1f044c1b03591873b1c1a655ce537d93","observation_id":"1ddc6faa-2fb1-458d-897b-9324c98a28c2","resolution":{"observed_at":"2026-08-07T05:21:09.689345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07646","last_updated":"2023-03-06T06:28:18Z","snapshot_observed_at":"2026-08-03T19:51:05.627063Z","submitted_at":"2022-02-15T18:48:31Z","title":"Quantifying Memorization Across Neural Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07646","snapshot_observed_at":"2026-08-07T05:21:07.451991Z","title":"Quantifying memorization across neural language models.arXiv preprint arXiv:2202.07646, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.451991Z"},"links":{"cited_paper":"/paper/2202.07646","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:8990a09f354a4e7e2dc8362970f2ce26a31a1fa03a0a946dec45fea29bda77cc","observation_id":"e396fb1f-1f7e-429f-aff8-5366799e8cf3","resolution":{"observed_at":"2026-08-07T05:21:07.451991Z","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":"2026-08-07T05:21:09.632474Z","title":"Extract- ing training data from diffusion models","venue":null,"work_id":"0ef40565-d087-4918-ad3c-3483e4f37d2a","year":2023},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.461451Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ad8408ca546409d98dcdffa030a909f7ef9b1c75f5cf274de3fd6d7f870d987c","observation_id":"08e26cdb-be78-41e0-a4f9-c6196eee2acc","resolution":{"observed_at":"2026-08-07T05:21:09.642870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.603827Z","title":"Fowl, et al","venue":null,"work_id":"f5525dab-6d9b-47b2-b082-e8e14fe46f22","year":2023},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.477733Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:f2d145f967dbc4b1cda22ed64f96ca011ab1af301d354ac165706503d9bae1b9","observation_id":"4a14afc2-1276-480e-81de-3ce99f11ec74","resolution":{"observed_at":"2026-08-07T05:21:09.610723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.580756Z","title":"Revealing and protecting labels in distributed training","venue":null,"work_id":"7a0a0cc4-2fd7-4a91-aac7-24de6d7ed1ae","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.487426Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:02e20fc9a431be18883ce760729621b8452b97fd462af78e98378940360867cf","observation_id":"79f21347-cc1d-4a22-b9d5-0bcfa3c006c5","resolution":{"observed_at":"2026-08-07T05:21:09.587690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.554483Z","title":"Federated learning for predicting clini- cal outcomes in patients with covid-19.Nature medicine, 27(10):1735–1743, 2021","venue":null,"work_id":"6fe7a29b-422b-4b46-a498-64184f4031e1","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.502094Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:55b2022a9446bd7116f8ec447c987747e999b66ae18d5d676a668596880576cd","observation_id":"d493afd7-a1e4-4fe7-ba6e-1f09f6c029cc","resolution":{"observed_at":"2026-08-07T05:21:09.561974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.522739Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"30525406-a129-4f27-990f-90535c9fc9ae","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.510866Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:e36dd7d9fa3fb33d844b9f5c95a56e115d94a634d33f028ac336bb209aa58e2e","observation_id":"6ef9a326-6c42-4221-9629-f81f56635907","resolution":{"observed_at":"2026-08-07T05:21:09.529284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05403","last_updated":"2025-02-05T03:07:53Z","snapshot_observed_at":"2026-08-10T00:35:31.825746Z","submitted_at":"2024-04-08T11:05:45Z","title":"SoK: On Gradient Leakage in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05403","snapshot_observed_at":"2026-08-07T05:21:07.522312Z","title":"Sok: Gradient leakage in federated learning.CoRR, abs/2404.05403, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.522312Z"},"links":{"cited_paper":"/paper/2404.05403","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:aa5c37f60c149579beef4636843ad04376767c0094f9bfc1ce949a0af2628e60","observation_id":"fddffd70-e77a-48b9-badd-7c4ce081bbca","resolution":{"observed_at":"2026-08-07T05:21:07.522312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:21:07.528581Z","title":"The algorithmic foundations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3–4):211– 407, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.528581Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:d9ae3311668423d736719dd80cfc5d2988342343458fd4fbc07270c63bbf0eee","observation_id":"4bbc4dfb-985d-46a4-8a4e-cc5916d66dd2","resolution":{"observed_at":"2026-08-07T05:21:07.528581Z","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":"2026-08-07T05:21:09.470676Z","title":"Exploiting pre-trained models and low- frequency preference for cost-effective transfer-based attack.ACM Trans","venue":null,"work_id":"1f18b825-7d30-4cc8-abd7-053f739f85a1","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.537406Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0b6cd2d467781f9573f0f9bb4d04e9bdd6e08b33fe390d4ed53d82aa9295fc18","observation_id":"6ea651b7-84c0-4f46-bbff-6ca5898b7a0a","resolution":{"observed_at":"2026-08-07T05:21:09.482115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.432960Z","title":"Guardian: Guarding against gradient leakage with provable de- fense for federated learning","venue":null,"work_id":"d532ea61-841c-4ad3-9c7b-1a42c7f04769","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.544136Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:5772a47d4f3c11a38ce3eefbfc67a1bccb17072d048d5b020edf8905024dfaf3","observation_id":"a65a9c26-a031-42e8-baaf-d795715a04fb","resolution":{"observed_at":"2026-08-07T05:21:09.445070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.405646Z","title":"On the trustworthiness landscape of state-of-the-art generative models: A survey and outlook","venue":null,"work_id":"d02e5eaf-4791-4e48-9949-9f2c3bf9e10e","year":2025},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.550427Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:e221ff32239bf52669cf05af092ee53ce267fff5ed38d8475e2c4353a3904a1b","observation_id":"82ad1355-48b2-4865-972d-4c29225b75ff","resolution":{"observed_at":"2026-08-07T05:21:09.415622Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.380279Z","title":"Adap dp-fl: Differ- entially private federated learning with adaptive noise","venue":null,"work_id":"905304dc-e1d7-4508-ae89-9e4302f97b0a","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.564470Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0c7a85332fd15ebb36d875cab9df8ff411440e6f06c5909232f59cf529e0e88a","observation_id":"1beb56c3-de7e-427f-ba15-6c5ada9528b5","resolution":{"observed_at":"2026-08-07T05:21:09.388212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.353815Z","title":"Inverting gradients-how easy is it to break privacy in federated learning? InNeurIPS, volume 33, pages 16937–16947, 2020","venue":null,"work_id":"77830667-69a8-4b6a-a6a1-86f3ec0e0306","year":2020},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.571248Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:29ab9e8d7615f6b7be722da515e31e3c81b00fbb964f81c37c9050c6e3f6f639","observation_id":"0c99c892-eccc-4f3b-9f0f-4c1cb9d6195d","resolution":{"observed_at":"2026-08-07T05:21:09.364103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.07557","last_updated":"2018-03-01T10:12:27Z","snapshot_observed_at":"2026-07-06T06:15:22.497001Z","submitted_at":"2017-12-20T16:28:37Z","title":"Differentially Private Federated Learning: A Client Level Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.07557","snapshot_observed_at":"2026-08-07T05:21:07.578825Z","title":"Differen- tially private federated learning: A client level perspec- tive.arXiv preprint arXiv:1712.07557, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.578825Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:031b8b86517df12a82de993df9f1b57d1ae90ff0c7c2c076ebfa771d91762673","observation_id":"d4f64195-8ae1-497a-89bc-b63526b4e08f","resolution":{"observed_at":"2026-08-07T05:21:07.578825Z","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":"2026-08-07T05:21:09.329278Z","title":"Federated learning for medical image anal- ysis: A survey.Pattern Recognit., 151:110424, 2024","venue":null,"work_id":"12a78381-1647-4c8b-a519-93d3b61a4500","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.592358Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ad26ec799e28de2b5426cc6c87f96b3ee54b4c2df3f680ff57e2cfa85937bab2","observation_id":"9b3f3164-1afd-4a51-8474-3a4da049374e","resolution":{"observed_at":"2026-08-07T05:21:09.337575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.298345Z","title":"Does dif- ferential privacy really protect federated learning from gradient leakage attacks?IEEE Transactions on Mobile Computing, 2024","venue":null,"work_id":"a7de8b59-7036-462a-993e-19d45bd3f7f3","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.603447Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:dc6de2d70c93582c4ff0061988f2de79df51b9d4cd1b36070744db511ab05795","observation_id":"bc364678-4e49-4b5d-bd57-d0426629806f","resolution":{"observed_at":"2026-08-07T05:21:09.307723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.254775Z","title":"Eval- uating gradient inversion attacks and defenses in feder- ated learning","venue":null,"work_id":"517bc48f-243a-4f65-bb5f-751c79925b1a","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.610710Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ea07d91164e31d08f69495f5c985f4c9e7989c0070b0d45605209e7a5bf029e1","observation_id":"bc7c7b86-b32f-494c-8940-49e98d80665e","resolution":{"observed_at":"2026-08-07T05:21:09.265109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.227167Z","title":"Gra- dient inversion with generative image prior","venue":null,"work_id":"f99b826c-adc4-45cb-ad81-6335c8a5ac2f","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.616707Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:a95da117e296a8a198723c53a3e571057c8a2475a95b569375a2ae6ffaba5aa5","observation_id":"e84cd974-34e3-46f9-9909-77615cbc2f05","resolution":{"observed_at":"2026-08-07T05:21:09.233924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12328","last_updated":"2022-02-09T04:55:14Z","snapshot_observed_at":"2026-08-04T13:45:26.163424Z","submitted_at":"2022-01-28T18:48:18Z","title":"Toward Training at ImageNet Scale with Differential Privacy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12328","snapshot_observed_at":"2026-08-07T05:21:07.622647Z","title":"Toward training at imagenet scale with differential pri- vacy.CoRR, abs/2201.12328, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.622647Z"},"links":{"cited_paper":"/paper/2201.12328","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0bdf4be91b6727c373ee3bc91376b7d340ac6a3a1b65c7d2c5ac2754c9cde43d","observation_id":"2bf75c8c-3793-49f2-b04a-e818d50d5c92","resolution":{"observed_at":"2026-08-07T05:21:07.622647Z","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":"2026-08-07T05:21:09.201343Z","title":"An international study presenting a federated learning ai platform for pediatric brain tumors.Nature communica- tions, 15(1):7615, 2024","venue":null,"work_id":"a82e7b41-7148-40c4-aa85-7fe1990d97ca","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.630765Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:81a094040520000d7253edd5bebe3201d8cf5c9a3cd9c096ad168ea2f1034152","observation_id":"0dd5965e-4ff0-4b33-8cc9-4430a4f4746a","resolution":{"observed_at":"2026-08-07T05:21:09.209779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.160868Z","title":"On the convergence of fedavg on non-iid data","venue":null,"work_id":"57172725-e165-4af5-a147-01e338dd3c35","year":2020},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.637503Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0201bcc633133615619fdbc6c283cbdfdfb361f362808a0874d38c6154c69144","observation_id":"47584a1b-4dae-4350-b212-b4da184e2a01","resolution":{"observed_at":"2026-08-07T05:21:09.179053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.126024Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization","venue":null,"work_id":"6325f033-46cb-4dc1-a592-25480e40a560","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.645134Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:a959ca135c10729e4fadcc72be40b546521ea7fe7fe0c511c0aaeafc419ec657","observation_id":"f4dd3469-15cd-436d-a8b2-147d03cc9145","resolution":{"observed_at":"2026-08-07T05:21:09.135431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.098759Z","title":"Auditing privacy defenses in federated learning via gen- erative gradient leakage","venue":null,"work_id":"772ab351-fe09-47d9-aaed-3128b38cc334","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.652928Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:923eab0c0047ca8abac7833fc5e0e0e2cf9b64b8357928613b0b0f8242f54ab1","observation_id":"fe245c1f-f2b2-457a-bdec-6c82cd6fa112","resolution":{"observed_at":"2026-08-07T05:21:09.108130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.064483Z","title":"Backdoor defense with machine unlearning","venue":null,"work_id":"4702d891-8f32-453b-bfb2-18186804b63d","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.662010Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:200f84481760287b96ad15585e7f54836e858c44a063bc5258e71f7929bb1cfe","observation_id":"8364c06d-669a-4f15-bc5d-157bca4f5947","resolution":{"observed_at":"2026-08-07T05:21:09.075164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.031629Z","title":"Pre- dicting treatment response in multicenter non-small cell lung cancer patients based on federated learning.BMC cancer, 24(1):688, 2024","venue":null,"work_id":"25a22d6a-9fcf-467b-810e-079bad0a068a","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.671838Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:3b93ce46ea31511c9e70fba7a96cdcdf971193bac42dc130bafa073e34f00798","observation_id":"ccdf2b88-24e3-4295-a6e8-3a58d50257f4","resolution":{"observed_at":"2026-08-07T05:21:09.038892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:09.006419Z","title":"SGDR: stochastic gradient descent with warm restarts","venue":null,"work_id":"d494a4ae-bcbb-4c6e-a4a3-1506d333c6d0","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.678622Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:5646e98c767138ba5bd6c8c3d6595bbab184458b93f1e1758481c591584caa79","observation_id":"5f0f3f96-f468-46b3-a4fd-441c6226e8cc","resolution":{"observed_at":"2026-08-07T05:21:09.013707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.978507Z","title":"A tutorial on fisher information.Journal of Mathemati- cal Psychology, 80:40–55, 2017","venue":null,"work_id":"5a07951f-661f-443e-a6a4-569ce2f04510","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.692532Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:7aa02a6ec7288923548394bbc62e78487bc1ad4e2e89fb6ad94fa260fd7c37d3","observation_id":"377071ac-48b0-413a-8996-3780cf0682c5","resolution":{"observed_at":"2026-08-07T05:21:08.987624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.935740Z","title":"Instance-wise batch label restoration via gradients in federated learning","venue":null,"work_id":"f9044b1d-c1c2-4e60-9802-30e96014425c","year":2023},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.701121Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:0a21f7c34a7cba6f8dd6d61e84da924ea246d3502234c2b3a097b9ada5da651d","observation_id":"2a99f17a-e1bd-4e5b-a4f8-e5bf8d3ffe53","resolution":{"observed_at":"2026-08-07T05:21:08.951107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.909724Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"e64fc7de-1b57-44e8-b381-d97adad560fb","year":2018},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.706917Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:f6734b41fea8658e08ae4357d232eebe80b20648a96f1e0c21f0fe0b89455067","observation_id":"1a00360c-fd57-4c4c-b76e-f25c4c25b1cb","resolution":{"observed_at":"2026-08-07T05:21:08.921003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.869401Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"445e64e8-c5a6-48ca-a663-0f982f72a277","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.712483Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:090a530d09fa88792b529583c38ce64cb6e57b526c973333d3f5c49d44fc4265","observation_id":"189fcdb1-ae2b-4b0c-9779-765b4ba71463","resolution":{"observed_at":"2026-08-07T05:21:08.878843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.838165Z","title":"Transforming large-size to lightweight deep neural networks for iot applications","venue":null,"work_id":"4445095b-7301-4bf0-b760-9c15c0c07d1a","year":2023},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.722652Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:3648ca1a5ef8003ac085a6a48e13d78ab2134091cf9f785753c0580bcaf5e1c2","observation_id":"942e7c29-210a-4d1f-a2a7-a8b32b35a4d3","resolution":{"observed_at":"2026-08-07T05:21:08.846426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.813269Z","title":"Secureml: A system for scalable privacy-preserving machine learning","venue":null,"work_id":"1ac0544d-b102-472d-9b3b-921121b54365","year":2017},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.729855Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:c7199d876ec7ad0216d4450c721eef5453dbb641083ec12afaf4b1d7d2c733bd","observation_id":"38436d76-4951-43eb-86ad-2ecddc1a4aac","resolution":{"observed_at":"2026-08-07T05:21:08.819035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.776970Z","title":"Nguyen, Ming Ding, Pubudu N","venue":null,"work_id":"16ccda34-3717-4c8d-a162-039adf301135","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.741867Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:863330710f005d2d1330cdff2e7574f4a9795e10de1b84c33492d2796642bb5f","observation_id":"088f02c1-8cb6-483c-9e40-06ee58918bdb","resolution":{"observed_at":"2026-08-07T05:21:08.787150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.740048Z","title":"Eluding secure aggregation in federated learning via model inconsistency","venue":null,"work_id":"65f42e02-558b-4c1b-8ec8-bc130c76478a","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.752912Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:073b80141c921deddfa130d3bb60ff3b3c5ae124f328ce64e5d240dbeb8db7d1","observation_id":"a4ab9c0a-53ba-471c-9198-c38320c3d966","resolution":{"observed_at":"2026-08-07T05:21:08.755629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.716334Z","title":"A survey on deep learning: Algorithms, techniques, and applica- tions.ACM computing surveys, 51(5):1–36, 2018","venue":null,"work_id":"85eb24be-af2c-46e3-87f7-afd247b98738","year":2018},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.759130Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ad8fa82677bdf0f9abeb4cf8b3d91690920aec84522fbb9cd6bc19723b5b52b2","observation_id":"6d550a7f-83fb-4f64-be11-7f9f708fcbae","resolution":{"observed_at":"2026-08-07T05:21:08.723054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.676193Z","title":"Federated learning in medicine: facil- itating multi-institutional collaborations without sharing patient data.Scientific reports, 10(1):12598, 2020","venue":null,"work_id":"2280a4f4-95b7-4dae-8e27-3556220994be","year":2020},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.767340Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:102d1ea05f646b937a15fc92dc96da30dfc446a6fb917b0a35c5084bed85e126","observation_id":"422902f2-b10d-43ae-a303-6cbf20a0ad00","resolution":{"observed_at":"2026-08-07T05:21:08.688321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.641569Z","title":"Soteria: Provable defense against privacy leakage in federated learning from representation perspective","venue":null,"work_id":"f5d025d6-38ec-4468-ab63-dfe886c327da","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.776753Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:6126ab2ebda8cabdd28616b8e4c23cdd0f5f7f1f8f74d2effd7471b83d2b31a9","observation_id":"90172792-a91e-4a35-b7e4-517c335f813f","resolution":{"observed_at":"2026-08-07T05:21:08.650122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:21:07.785834Z","title":"More than enough is too much: Adaptive defenses against gradient leakage in production federated learning.IEEE/ACM Transactions on Networking, 32(4):3061–3075, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.785834Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:3dc593343c436dc4ed71036896785a6a614110d3e7c4e26c3cc8ca773a61068b","observation_id":"e7fe7c36-806a-441f-b768-2cc4b58c59cc","resolution":{"observed_at":"2026-08-07T05:21:07.785834Z","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":"2026-08-07T05:21:08.614497Z","title":"Pro- tect privacy from gradient leakage attack in federated learning","venue":null,"work_id":"08ea3dfa-4507-42cf-a981-c9b43ed2dcdb","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.796280Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:824f75a7c1ea8daba893ca92afb5338bae0e9e9a77dccc25bf0bc14d7069814c","observation_id":"15185ed2-6d2e-4188-82d2-ebac4c5c6efb","resolution":{"observed_at":"2026-08-07T05:21:08.622107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15731","last_updated":"2024-06-22T04:42:18Z","snapshot_observed_at":"2026-07-06T18:35:17.953523Z","submitted_at":"2024-06-22T04:42:18Z","title":"Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15731","snapshot_observed_at":"2026-08-07T05:21:07.807147Z","title":"Break- ing secure aggregation: Label leakage from aggre- gated gradients in federated learning.arXiv preprint arXiv:2406.15731, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.807147Z"},"links":{"cited_paper":"/paper/2406.15731","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:85155d53269e162866b39705b9c237bb3b1444011bd825954463ba7f95608996","observation_id":"04aa43cb-d45a-4068-a46d-b0f49ef829fb","resolution":{"observed_at":"2026-08-07T05:21:07.807147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.10397","last_updated":"2020-04-23T04:31:26Z","snapshot_observed_at":"2026-08-02T05:12:09.916792Z","submitted_at":"2020-04-22T05:15:03Z","title":"A Framework for Evaluating Gradient Leakage Attacks in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.10397","snapshot_observed_at":"2026-08-07T05:21:07.818791Z","title":"A frame- work for evaluating gradient leakage attacks in federated learning.CoRR, abs/2004.10397, 2020","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.818791Z"},"links":{"cited_paper":"/paper/2004.10397","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:a79afc742023eeb5ce290083ba19fcb2543d70e4d1984a2a47e0520b1bc9741e","observation_id":"77037d7f-d0e3-4f4a-816e-9d058f04dc37","resolution":{"observed_at":"2026-08-07T05:21:07.818791Z","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":"2026-08-07T05:21:08.580556Z","title":"Fishing for user data in large-batch federated learning via gradient magnification","venue":null,"work_id":"d7aef8ce-a5c6-4965-8325-29b72c05c509","year":2022},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.830148Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:eeb5a288c38431cd2570df623bfa89ebd300775d6783149f427123535b55edf4","observation_id":"c536d06c-e135-4095-8fa6-77b42e77f8f8","resolution":{"observed_at":"2026-08-07T05:21:08.590070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.551321Z","title":"See through gradients: Image batch recovery via gradinver- sion","venue":null,"work_id":"cf120b3b-33ce-4d24-92d2-73031b90860c","year":2021},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.839373Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:b1d41099d1bb308407323757064c61f150c20c712c89b53191f987ad152081fa","observation_id":"c65b002a-bddc-45a1-9d6f-3975b4e4c5f5","resolution":{"observed_at":"2026-08-07T05:21:08.560646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.526647Z","title":"Gradient obfuscation gives a false sense of security in federated learning","venue":null,"work_id":"a58d3967-3987-48a2-9606-f28062927ca1","year":2023},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.846495Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:e3a21f11b9ba8f0c60ec694382bcc59bddeb0097dd56a0500761f8c015f1d1a9","observation_id":"5ead6bad-755b-4fc2-a2d1-3a61d12735a5","resolution":{"observed_at":"2026-08-07T05:21:08.534078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.474681Z","title":"BatchCrypt: Efficient homomorphic encryption for Cross-Silo federated learning","venue":null,"work_id":"a104069c-6c35-4d92-8c5b-226fc9724ea5","year":2020},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.858898Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:ac6ac1d4a59f212d98101e0b141c2e8ce203fb43ee64173f0946df9352149603","observation_id":"6a9cf947-30a4-44fa-a940-7670dde65541","resolution":{"observed_at":"2026-08-07T05:21:08.494231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.437900Z","title":"Re- cent methodological advances in federated learning for healthcare.Patterns, 5(6):101006, 2024","venue":null,"work_id":"dcc5ec4a-0214-4ee5-9c3b-b692e335f3e6","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.866700Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:3aae1c08c942fa5be7d0c7da999c00196fca6551c09b598885f41d875e9e8148","observation_id":"a633855e-9a40-4c30-97af-1230c5350be3","resolution":{"observed_at":"2026-08-07T05:21:08.450609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:07.883060Z","title":"idlg: Improved deep leakage from gradients.arXiv preprint arXiv:2001.02610, 2020","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.883060Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:70e98d9152f886b6f68261094a6e7a6f98e03e80def90aea5603fa802e563d6a","observation_id":"5d98bd3f-28a8-4af1-a2fa-5b5867e4f17f","resolution":{"observed_at":"2026-08-07T05:21:07.883060Z","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":"2026-08-07T05:21:08.401600Z","title":"Zhao, Atul Sharma, Ahmed Roushdy Elko- rdy, et al","venue":null,"work_id":"84dad8fa-ebd7-4dee-afa6-609b4ac13723","year":2024},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.894071Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:78e114856e519cc96ecae5ab13b797d1781f278a044295a916952b7c06756f6d","observation_id":"35eab061-2342-4ce5-8e68-4b5c2b0cd79b","resolution":{"observed_at":"2026-08-07T05:21:08.418465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T05:21:08.370378Z","title":"specific/common parameters","venue":null,"work_id":"f5660e9d-f4fb-4b4e-bd1b-47cf02c36c54","year":2019},"citing_paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T05:21:07.900685Z"},"links":{"citing_paper":"/paper/2506.08435"},"observation_digest":"sha256:e10b35bb636173d66c0a8679262eca78cf9a457fd6cf1bc16b26df317db2effe","observation_id":"734a47e1-689b-409f-a1e1-25e4910b9c1a","resolution":{"observed_at":"2026-08-07T05:21:08.379623Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.08435","last_updated":"2025-06-10T04:17:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T16:54:25.687263Z","submitted_at":"2025-06-10T04:17:06Z","title":"Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":47},"total_outbound_references":58},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 0 inbound Pith citation observations for arXiv:2506.08435."}