{"as_of":"2026-08-09T23:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4f76eb988347f3039a454dfa36a3f6a13ac00b8218c99cdfcfe2cdfa437e5bd3","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:56:02.228729Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"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/2507.09602/citation-record","integrity":"/paper/2507.09602/integrity","json":"/paper/2507.09602/citation-record.json","paper":"/paper/2507.09602"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:03.137624Z","title":null,"venue":null,"work_id":"806ef78b-470e-45c8-b067-e25ca95fd710","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.981227Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:73e30008cfd26c8dc89c8b526ddfab4057b75b9c1e17547fd6383e8969c98b9d","observation_id":"02985910-24fb-4373-a4ae-ee757d41a99a","resolution":{"observed_at":"2026-08-06T17:56:03.143134Z","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":"2026-08-06T17:56:03.115903Z","title":"MSE is a metric used to measure the average squared differences between corresponding pixels of two images","venue":null,"work_id":"8822c7db-83b0-4061-9cb0-4aa020c1885a","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.986843Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:ff5b9eb75d6cf6b4a2b1a1a4104ee3123e302dac2dbaf9bd366c4dbd72fbd203","observation_id":"435faf4f-d0ce-41bf-a97e-1bf245add1bd","resolution":{"observed_at":"2026-08-06T17:56:03.121906Z","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":"2026-08-06T17:56:03.097037Z","title":"Exploiting subtle differences in gradients before and after data removal, the DLG attack reconstructs sensitive data points by comparing gradients from the gl obal model","venue":null,"work_id":"6d15a4e0-1eba-4b9f-a08c-cb025a1a4a56","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.991387Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:28f31955c04bc5ac63de7154cbc295d29b0d25166d6f7eddc91b06495e9bd554","observation_id":"ea04ac53-6dda-46c6-88bd-3ab99f088590","resolution":{"observed_at":"2026-08-06T17:56:03.102292Z","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":"2026-08-06T17:56:03.078762Z","title":"Part\" subset, corresponding to the retained gradients, while the gradients of the remaining 12 images were forgotten. As the reconstruction progresses, it is observed that the","venue":null,"work_id":"d8bd3ff1-f5ff-4491-b77f-3e08f41248c2","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.996171Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:d98567d0d43f251d00f72d5742e886ac67371fa9a5f5a656bf0d9f1692e5bbdf","observation_id":"1af4243e-dfa0-4485-9c45-ab2de5fef67b","resolution":{"observed_at":"2026-08-06T17:56:03.084173Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:56:02.984715Z","title":"Federated conformal predictors for distributed uncertainty quantification,","venue":null,"work_id":"0b9e5154-259e-4717-af0a-ab59dc42a1de","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.024386Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:54889f39112b98ec007538739c89618726b3e4a71f589470d9da06536d29bd0c","observation_id":"c2273d8a-e8f4-4cf3-9bf5-c4e6d6af7c59","resolution":{"observed_at":"2026-08-06T17:56:02.989738Z","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":"2302.08888","last_updated":"2023-05-06T02:26:32Z","snapshot_observed_at":"2026-07-06T14:52:56.806494Z","submitted_at":"2023-02-17T14:17:44Z","title":"Multimodal Federated Learning via Contrastive Representation Ensemble","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.08888","snapshot_observed_at":"2026-08-06T17:56:02.030115Z","title":"Multimodal federated learning via contrastive representation ensemble,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.030115Z"},"links":{"cited_paper":"/paper/2302.08888","citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:c5aa96cff9c42134065791c5f60c5f6d9d7a34c08000441d3e0798c1d9bcdfbc","observation_id":"e415181d-e01e-4eea-b643-22be44bfd305","resolution":{"observed_at":"2026-08-06T17:56:02.030115Z","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":"2026-08-06T17:56:02.969153Z","title":"General data protection regulation (GDPR),","venue":null,"work_id":"a7c49257-e8a3-4ae7-8130-16bf99aee55c","year":2018},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.037069Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:4900955d17bcbad1b495d56f5c226e5700a352558fbe1c2fe9710d1c8e7e1fca","observation_id":"d892d621-bb26-4ab1-9d5b-f556eba81670","resolution":{"observed_at":"2026-08-06T17:56:02.974237Z","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":"2026-08-06T17:56:02.948979Z","title":"Understanding the scope and impact of the california consumer privacy act of 2018,","venue":null,"work_id":"39d0b6db-d800-4587-90f9-c100223195fa","year":2018},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.042307Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:1287bbbebb89d176b921ccec01b11c8842ff791e8060dcc4975ec78f89b99ca6","observation_id":"986f5f43-594a-4b97-9fdc-b3cda668406f","resolution":{"observed_at":"2026-08-06T17:56:02.955832Z","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":"2026-08-06T17:56:03.236484Z","title":"Wu et al","venue":null,"work_id":"70385938-aded-4041-af92-d21fade49f36","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.953971Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:226259a7b7eaa91c78942cff8bd51179fcd786014fce94dab3d084f830649121","observation_id":"a11683be-29a1-482f-8f9c-d8408ae2d8f6","resolution":{"observed_at":"2026-08-06T17:56:03.245594Z","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":"2026-08-06T17:56:03.059588Z","title":"Secure and efficient federated learning with provable performance guarantees via stochastic quantization,","venue":null,"work_id":"e3f2da26-2555-43aa-a19d-3af44db545b6","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.001607Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:df6765b5a29f7aaa4f3d3982a108b6cbed8788b0a368123855cc029ebb99831b","observation_id":"132b755a-743b-4535-9feb-f93d18e35946","resolution":{"observed_at":"2026-08-06T17:56:03.065636Z","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":"2026-08-06T17:56:03.040802Z","title":"Toward secure and verifiable hybrid federated learning,","venue":null,"work_id":"be00dee2-ce17-4ec6-be2d-f62c4df4dd11","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.007100Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:bcddd25bd6e13b422237ac6a4c0937d0dc78c2aea817d80f8c7b1d02bbbccbd0","observation_id":"a3ed1e71-3f60-4659-8cb9-86f52d7ef76b","resolution":{"observed_at":"2026-08-06T17:56:03.046684Z","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":"2026-08-06T17:56:03.019893Z","title":"Reliable and interpretable personalized federated learning,","venue":null,"work_id":"af8df1d7-6b8a-4d8c-8a04-ac98c030ba9f","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.012709Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:0e998d669b20ec0e3c6b5ad729fc43678f569b28b2d0f58ff8ec58a0c1f8d1a6","observation_id":"04b68458-282b-4ff7-afc8-c81892bb2690","resolution":{"observed_at":"2026-08-06T17:56:03.026297Z","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":"2026-08-06T17:56:03.001266Z","title":"Revisiting weighted aggregation in federated learning with neural networks,","venue":null,"work_id":"bbf43651-db46-4913-a98e-3b67a0a16147","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.018785Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:0ea9861c1a9e249886ad958e8f4da51780b02cbe59491c3bae5968200baa370b","observation_id":"ce1814bf-4bce-4e7f-958b-63ee920d2a3b","resolution":{"observed_at":"2026-08-06T17:56:03.007143Z","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":"2026-08-06T17:56:02.824206Z","title":"Fedrecovery: Differentially private machine unlearning for federated learning frameworks,","venue":null,"work_id":"7f976e17-af1e-453e-b511-cbc501474856","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.079823Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:14c120ec62d18a0fe56e1ed6fc806e552b94368173f4d15a4bc7d72cc51d2ea0","observation_id":"ee7b4af2-00c3-4e40-8607-449d1f7cdfc0","resolution":{"observed_at":"2026-08-06T17:56:02.831148Z","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":"2026-08-06T17:56:02.804349Z","title":"Guaranteeing data privacy in federated unlearning with dynamic user participation,","venue":null,"work_id":"c539aeff-bf8e-4ae9-bc8f-4e92f2100a01","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.085004Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:8a212ee479f6ab56163267a447044d3574b1cddd82d820db3485f300d2de0968","observation_id":"745eacbb-4fba-47de-924d-c49a22b1055c","resolution":{"observed_at":"2026-08-06T17:56:02.810394Z","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":"2026-08-06T17:56:02.783305Z","title":"Privacy-preserving federated unlearning with certified client removal,","venue":null,"work_id":"6a8317fa-f659-4958-9c76-3fada3134c1d","year":2025},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.090286Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:d88a3885551c2a6f2bdc90e6f60dd1ef08943ef5ea3694f87e9c9e63b1983d70","observation_id":"66766310-9c99-4b21-b8c8-8968bba89251","resolution":{"observed_at":"2026-08-06T17:56:02.790948Z","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":"2026-08-06T17:56:02.764875Z","title":"Federated unlearning and its privacy threats,","venue":null,"work_id":"832c3dd5-5a58-45b2-b631-32af8293925f","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.095243Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:7f54abfe9aee48296f31e6492a2698ee6dbcc0e95c423dfee8c50b70f8d4c309","observation_id":"ad71e60c-62d8-4816-b89e-a232fbca3955","resolution":{"observed_at":"2026-08-06T17:56:02.770566Z","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":"2026-08-06T17:56:02.928562Z","title":"Federaser: Enabling efficient client- level data removal from federated learning models,","venue":null,"work_id":"fd77b159-c891-4d65-8542-54f16bba0cac","year":2021},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.048759Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:9fafc7a14389c95bc5c4d62bdf70e99b39636a4a5352d511b0a2531600ff1ae7","observation_id":"24b392ed-0743-4e48-b6c2-d77e953afa78","resolution":{"observed_at":"2026-08-06T17:56:02.935008Z","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":"2026-08-06T17:56:02.905361Z","title":"A survey on federated unlearning: Challenges, methods, and future directions,","venue":null,"work_id":"d6427e77-e4c8-4909-a766-e00ca4c9a987","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.055032Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:c9487ac1d74b5f7f1d8d0b53d02e9d3c785ebe4867b1fa49cd1b91571602907f","observation_id":"34b7a254-f639-4b3d-91b0-6e30b843f4c0","resolution":{"observed_at":"2026-08-06T17:56:02.910858Z","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":"2026-08-06T17:56:03.218712Z","title":"In addition, Wang et al","venue":null,"work_id":"f190d58f-6d6c-41dc-b6ff-14a6045b51d0","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.959225Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:6f6f2135c48c7acd04559b9413ddb0f1699bc8453e932fc68e19f2bd15579514","observation_id":"ab91dbc8-3585-4efb-8c0f-29b11f04d229","resolution":{"observed_at":"2026-08-06T17:56:03.223534Z","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":"2026-08-06T17:56:02.888627Z","title":"Asynchronous federated unlearning,","venue":null,"work_id":"e0f73f27-7fd3-4216-b311-285793ac4f4d","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.060687Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:7e7875e21440634d562a49ac5a9cc3d0c26b934a743aff0e3e0305a101c8aafd","observation_id":"5387bcee-c2d3-4037-86e8-dbcd3c3794bb","resolution":{"observed_at":"2026-08-06T17:56:02.893888Z","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":"2026-08-06T17:56:02.870576Z","title":"Fast federated machine unlearning with nonlinear functional theory,","venue":null,"work_id":"ff11a57a-3bac-474e-a26c-f98430bfa193","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.065906Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:be5354e2e4285635ca32d3e555c7891d25f57713ca55cc5003057fd8913af921","observation_id":"4f9a5c5f-df25-4b21-b5f9-ef08bf5c455a","resolution":{"observed_at":"2026-08-06T17:56:02.876956Z","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":"2026-08-06T17:56:02.849758Z","title":"Verifi: Towards verifiable federated unlearning,","venue":null,"work_id":"7d327912-8ca5-4bbf-b295-d0b2c48fe330","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.071439Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:4c5794349d6a3c4647c076f1235318a19ef39a91064e5773379a29b9545d1894","observation_id":"68760636-c262-4109-99f1-b828ff956d98","resolution":{"observed_at":"2026-08-06T17:56:02.856281Z","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":"2026-08-06T17:56:02.131700Z","title":"idlg: Improved deep leakage from gradients,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.131700Z"},"links":{"cited_paper":"/paper/2001.02610","citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:b296ab9960dbdcf70381201e3c65462501d607b913bc397caa61a5d51acb5288","observation_id":"793c06aa-fdab-4f55-a089-40ecff933035","resolution":{"observed_at":"2026-08-06T17:56:02.131700Z","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":"2026-08-06T17:56:02.642078Z","title":"Inverting gradients-how easy is it to break privacy in federated learning?,","venue":null,"work_id":"32d51508-3c96-4cd0-8046-4719c8f928c3","year":2020},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.136834Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:110b54c7832782b7611e370a652fcc09c9b3a87d10586cb8c36e33196b3eba38","observation_id":"01c172fc-7aaf-486e-8bc9-cafc5215303a","resolution":{"observed_at":"2026-08-06T17:56:02.648811Z","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":"2026-08-06T17:56:02.621425Z","title":"See through gradients: Image batch recovery via gradinversion,","venue":null,"work_id":"debeb4d4-84ef-4234-b788-0b2f768e5120","year":2021},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.142051Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:4d85af1845d83195f194f298f504b1f94973cf1e95590c0c8e6f34d0a59353a9","observation_id":"59f5164a-abe8-45fb-a9ba-9aa3308b7b57","resolution":{"observed_at":"2026-08-06T17:56:02.628130Z","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":"2026-08-06T17:56:03.197089Z","title":"[28] who combined GAN priors with gradient-free optimizers to bypass existing defenses","venue":null,"work_id":"71379186-31b8-4c4a-9c6c-744c6c6bda16","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.964893Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:637747be7c6b6ed0e7b9f08d2bfc4b493e89d3c00f8480682b82cd061c573073","observation_id":"fcc5cba0-0a6e-41cc-bba4-fda6b08e21cc","resolution":{"observed_at":"2026-08-06T17:56:03.205792Z","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":"2026-08-06T17:56:02.746249Z","title":"When federated learning meets privacy -preserving computation,","venue":null,"work_id":"c855ca41-e87b-40d9-af87-d4448d78901a","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.100400Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:0e906454543b886ba1438cab7be8cf0ff4541516fefe1bc126aa7d61c6cffbbd","observation_id":"06e949d8-fb3a-4f41-a4fb-dc1b12b5c0aa","resolution":{"observed_at":"2026-08-06T17:56:02.753232Z","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":"2026-08-06T17:56:03.177161Z","title":"[30] proposed a generative gradient inversion framework that eliminates the need for iterative optimization through auxiliary data and feature separation techniques","venue":null,"work_id":"e9c316df-ccea-4c39-960b-a68c5893c24f","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.969959Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:6b9a199c66c88c41b4b252d905ce007c5c06fc8444e62a6bcc79968e95aec9cf","observation_id":"98791342-7739-4b99-8e3d-fb6e738d119a","resolution":{"observed_at":"2026-08-06T17:56:03.183970Z","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":"2026-08-06T17:56:02.727306Z","title":"Securing secure aggregation: Mitigating multi- round privacy leakage in federated learning,","venue":null,"work_id":"efa453fa-cbfd-417d-9017-503907c78d2f","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.105663Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:f5e00d3c201d88acb04f4388ec4643acef4a5372c72c73b1efff7120dd102918","observation_id":"88780fcd-1fda-4176-9dc6-450efbc5cc07","resolution":{"observed_at":"2026-08-06T17:56:02.732921Z","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":"2201.09441","last_updated":"2022-01-24T03:56:20Z","snapshot_observed_at":"2026-08-09T04:32:24.004839Z","submitted_at":"2022-01-24T03:56:20Z","title":"Federated Unlearning with Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09441","snapshot_observed_at":"2026-08-06T17:56:02.111172Z","title":"Federated unlearning with knowledge distillation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.111172Z"},"links":{"cited_paper":"/paper/2201.09441","citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:f3a4d6426bc187bb62a8040399febed7a5714353c6538019ddc85d6b475a1400","observation_id":"9cb9f0c4-6cd3-4b70-95cf-7ee729a9123f","resolution":{"observed_at":"2026-08-06T17:56:02.111172Z","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":"2026-08-06T17:56:02.708018Z","title":"Federated unlearning via classdiscriminative pruning,","venue":null,"work_id":"151b9299-e1d3-48ae-9f1e-43f38405e4cf","year":2022},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.116479Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:571246ae0c706ec13712d4011836abaa88e642ddee7e417dee24f011bcfd7860","observation_id":"6cc2f3fc-b66e-44c6-b885-896e690f505d","resolution":{"observed_at":"2026-08-06T17:56:02.715051Z","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":"2026-08-06T17:56:02.686456Z","title":"The right to be forgotten in federated learning: An efficient realization with rapid retraining,","venue":null,"work_id":"972459bc-4af9-4926-9ed5-f4cb57a1438f","year":2022},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.121245Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:c54596a8349d342b81af4c208efddd510f21d3cdd881187e1a30848e42d00f65","observation_id":"60c174eb-056c-4b71-8d10-d8cd7d5d38ae","resolution":{"observed_at":"2026-08-06T17:56:02.694838Z","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":"2026-08-06T17:56:03.155198Z","title":"honest-but-curious","venue":null,"work_id":"e0254eed-edc9-4d25-9200-69d2b8733ca4","year":null},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:01.974927Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:5776941483e16c69a2c903a0c0eda468dfa822e722b9380c63bca64c321c2efb","observation_id":"2366a008-56e3-4938-8413-b12e7ff22d22","resolution":{"observed_at":"2026-08-06T17:56:03.162515Z","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":"2026-08-06T17:56:02.663979Z","title":"Deep leakage from gradients,","venue":null,"work_id":"439a4fda-00d3-4a89-af12-a423dbd6e976","year":2019},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.126154Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:993ae1dfcf18e8a7a0b83b0cd067ac3dac8b61e2a7afde7b852fb9249e7ad074","observation_id":"d7036c3c-7a24-4463-aeb5-f11c66865149","resolution":{"observed_at":"2026-08-06T17:56:02.670401Z","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":"2026-08-06T17:56:02.601330Z","title":"Gradient inversion with generative image prior,","venue":null,"work_id":"a7c77149-b80a-4bb1-8361-ee45fa20086e","year":2021},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.148378Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:0021c2f60cee3be64ee4a0758d677ebddb83b640dd4fca16f4b490bbd8a61357","observation_id":"7615f89b-cee2-4655-8892-00f4adceff7d","resolution":{"observed_at":"2026-08-06T17:56:02.606353Z","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":"2026-08-06T17:56:02.582663Z","title":"Auditing privacy defenses in federated learning via generative gradient leakage,","venue":null,"work_id":"cf995e23-d1a5-4ad5-a2a6-2636c695720a","year":2022},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.154120Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:82c3f42c91fa5fa0b2d4022307818baecd4b1155fc4febc6d7a2184893660ae5","observation_id":"5bd1e343-2ca8-4f4a-ada6-7e0500d817d1","resolution":{"observed_at":"2026-08-06T17:56:02.589717Z","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":"2026-08-06T17:56:02.560546Z","title":"Gifd: A generative gradient inversion method with f eature domain optimization,","venue":null,"work_id":"7f269b75-cca1-4cd9-a087-c8e7013e9533","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.159877Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:dc2dd3cbd29263126946e9b955b14b5a815cd24ad42a64b2ee7239d57d9070b7","observation_id":"71cde58c-c783-4747-80fe-8ee04af6e165","resolution":{"observed_at":"2026-08-06T17:56:02.566477Z","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":"2026-08-06T17:56:02.538144Z","title":"Fast generation -based gradient leakage attacks: An approach to generate training data directly from the gradient,","venue":null,"work_id":"82845fd8-b1c5-426f-b4f7-b20cdc7ba5a1","year":2024},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.166055Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:4f99a4c81febfab698357b315ecff92f648b533fc9da40ab68413bdd80e29a7a","observation_id":"49cbcb4f-c172-4b75-a698-fa11cc1c0689","resolution":{"observed_at":"2026-08-06T17:56:02.546934Z","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":"2026-08-06T17:56:02.517747Z","title":"DGGI: Deep Generative Gradient Inversion with diffusion model,","venue":null,"work_id":"8a49aa1d-3c9f-4b5f-9f45-91dc896b02d9","year":2025},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.171335Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:cd1b5c0594d7a28e40dd5e5c847ac1430ef4a06150a29e326d2f6ee6bf2fc592","observation_id":"5cb40117-2e0c-4883-9e17-3a08695807c1","resolution":{"observed_at":"2026-08-06T17:56:02.525098Z","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":"2026-08-06T17:56:02.490660Z","title":"Secureml: A system for scalable privacy - preserving machine learning,","venue":null,"work_id":"cedb12c2-9edf-4559-b9c3-fe3e511c697f","year":2017},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.177430Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:7f6de7ad6b9b2f749cdc45bda134cdb4c6b3ea2f8a7dad88b940d533ac200d03","observation_id":"23194cec-9a1f-4d1e-9c73-d7a71c9e4757","resolution":{"observed_at":"2026-08-06T17:56:02.496623Z","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":"2026-08-06T17:56:02.470712Z","title":"QUOTIENT: Two-party secure neural network training and prediction,","venue":null,"work_id":"e8865782-cc93-48cb-9771-423f102bb3fc","year":2019},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.183402Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:fe814fe370e2387b5dc67425fa75d427bfc2aca1ba45475ea05af95be21b8d0b","observation_id":"7d43af15-3fdc-4bc5-9592-bc3affc4a7df","resolution":{"observed_at":"2026-08-06T17:56:02.476154Z","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":"1711.10677","last_updated":"2017-11-29T04:29:29Z","snapshot_observed_at":"2026-07-06T06:11:44.900667Z","submitted_at":"2017-11-29T04:29:29Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10677","snapshot_observed_at":"2026-08-06T17:56:02.189122Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.189122Z"},"links":{"cited_paper":"/paper/1711.10677","citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:18d0df2340c86c4f002209354a02882b2bc3cefe2b3901b022109dda8f3ffeb5","observation_id":"3c2c9d3a-6f62-45b1-ac4e-6aa3b31c8073","resolution":{"observed_at":"2026-08-06T17:56:02.189122Z","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":"2026-08-06T17:56:02.454374Z","title":"VerifyNet: Secure and verifiable federated learning,","venue":null,"work_id":"c98d1c6e-8aed-4927-9e4b-fb43c104fb93","year":2019},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.194755Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:4b756c0437496c5dc4cd8a4629c189a05d9fc25f213e875e65c50bdb26e073e5","observation_id":"579af876-c0f2-4c2f-8ff7-d90eddb21c1b","resolution":{"observed_at":"2026-08-06T17:56:02.460079Z","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":"2026-08-06T17:56:02.434261Z","title":"Exploiting unintended feature leakage in collaborative learning,","venue":null,"work_id":"1c61693f-46f2-43fd-b22b-4b444c67366a","year":2019},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.199940Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:447bef1678c6cecd9cf0741f946736c3c403497555e38aff632daff79937f33f","observation_id":"46dcd7a5-f899-4b06-bdd3-58286006db6d","resolution":{"observed_at":"2026-08-06T17:56:02.440175Z","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":"2026-08-06T17:56:02.418158Z","title":"Secureml: A system for scalable privacy- preserving machine learning,","venue":null,"work_id":"d9745d8b-b038-4777-809b-73bb40781802","year":2017},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.204659Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:10332ea714ba31885ebd4b07f20d47608bc0852f5e73aa5329ca9e9ed06a7743","observation_id":"742db4e4-fe75-4dfe-a7ff-e5e6717db26a","resolution":{"observed_at":"2026-08-06T17:56:02.423223Z","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":"2026-08-06T17:56:02.209538Z","title":"Differentially private federated learning: A client level perspective,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.209538Z"},"links":{"cited_paper":"/paper/1712.07557","citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:df6ba7d1a546417772a663accf0781773994123f076e97c9674f7d32ae375016","observation_id":"32512c88-49ef-4f07-9ca8-662973f22cc0","resolution":{"observed_at":"2026-08-06T17:56:02.209538Z","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":"2026-08-06T17:56:02.401737Z","title":"Gradient-leakage resilient federated learning,","venue":null,"work_id":"83337929-1e6b-4d97-a0aa-a751353ce8d6","year":2021},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.215097Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:b5d7fca7f1dc4a587bae3ffea3d3030b84266735ddf58e11ea061570a2ffb4e1","observation_id":"1273b1e5-3026-4cf1-90e7-51d251ab9fc4","resolution":{"observed_at":"2026-08-06T17:56:02.406634Z","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":"2026-08-06T17:56:02.385289Z","title":"Preserving data privacy in federated learning through large gradient pruning,","venue":null,"work_id":"d1a86a09-d3a6-459f-9197-72e81fdc4d19","year":2023},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.219527Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:c3cf5367f99db26c56fe4bba496a55f42b492a5004d754432abfe272fd744575","observation_id":"49f5d89b-9b03-4105-9f6d-eacf4ba5505c","resolution":{"observed_at":"2026-08-06T17:56:02.390277Z","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":"2026-08-06T17:56:02.370762Z","title":"Soteria: Provable defense against privacy leakage in federated learning from representation perspective,","venue":null,"work_id":"e0982b13-e7f2-4759-8798-3843cb81d880","year":2021},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.224157Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:286cf029b604a906c6eb033208357e29183287861716acabb31ff8a0508eab7a","observation_id":"703f02c8-dd2f-48c0-9ca4-d61effa39a01","resolution":{"observed_at":"2026-08-06T17:56:02.375466Z","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":"2026-08-06T17:56:02.347991Z","title":"A framework for evaluating client privacy leakages in federated learning,","venue":null,"work_id":"d4ddf30e-6074-4754-86f3-a4968234337c","year":2020},"citing_paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:02.228729Z"},"links":{"citing_paper":"/paper/2507.09602"},"observation_digest":"sha256:7de78cb2b9037ea98aa482cbb78bd0afd9f18dbb12c9f50eebcba83cc02b7df2","observation_id":"7e86ca70-e859-4090-9d99-c823de281d36","resolution":{"observed_at":"2026-08-06T17:56:02.356189Z","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"}}],"paper":{"arxiv_id":"2507.09602","last_updated":"2025-07-13T12:16:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T06:34:05.592099Z","submitted_at":"2025-07-13T12:16:43Z","title":"DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":51},"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 9 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2507.09602."}