{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WVOV2DCN2WEHLGD6DE7EMMPGLR","short_pith_number":"pith:WVOV2DCN","schema_version":"1.0","canonical_sha256":"b55d5d0c4dd58875987e193e4631e65c616b031cec0b3b21c1894dafe6e51e5f","source":{"kind":"arxiv","id":"2212.02042","version":3},"attestation_state":"computed","paper":{"title":"Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Cen Chen, Chengyu Wang, Mingyuan Fan, Wenmeng Zhou, Xiaodan Li","submitted_at":"2022-12-05T05:36:15Z","abstract_excerpt":"Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy protection capability of FL. In response, various defense mechanisms have been proposed to mitigate this threat by manipulating the uploaded gradients. Unfortunately, empirical evaluations have demonstrated limited resilience of these defenses against sophisticated attacks, indicating an urgent need for more effective defenses. In this paper, we explore a no"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.02042","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-05T05:36:15Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"18c8df9ee52cc66c6039a36e9e283b5de39ce90edf5cedd971ebdef69659c8d4","abstract_canon_sha256":"d99625c5f9d711b0fb63343ced08508cb5e3c42261b801652c59c147f77143a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:37.924864Z","signature_b64":"dWfHWRg6QOFRgJGPQpVz5Urc3/T/LWwA16ySfwr3OPHbXVfypqroLfzRosxUmKM+pTpbGmSa5e1pd/iAGcQhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b55d5d0c4dd58875987e193e4631e65c616b031cec0b3b21c1894dafe6e51e5f","last_reissued_at":"2026-07-05T11:18:37.924198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:37.924198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Cen Chen, Chengyu Wang, Mingyuan Fan, Wenmeng Zhou, Xiaodan Li","submitted_at":"2022-12-05T05:36:15Z","abstract_excerpt":"Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconstruct their sensitive data, thereby compromising the privacy protection capability of FL. In response, various defense mechanisms have been proposed to mitigate this threat by manipulating the uploaded gradients. Unfortunately, empirical evaluations have demonstrated limited resilience of these defenses against sophisticated attacks, indicating an urgent need for more effective defenses. In this paper, we explore a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.02042","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.02042/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.02042","created_at":"2026-07-05T11:18:37.924266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.02042v3","created_at":"2026-07-05T11:18:37.924266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.02042","created_at":"2026-07-05T11:18:37.924266+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVOV2DCN2WEH","created_at":"2026-07-05T11:18:37.924266+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVOV2DCN2WEHLGD6","created_at":"2026-07-05T11:18:37.924266+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVOV2DCN","created_at":"2026-07-05T11:18:37.924266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18934","citing_title":"Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Survey","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR","json":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR.json","graph_json":"https://pith.science/api/pith-number/WVOV2DCN2WEHLGD6DE7EMMPGLR/graph.json","events_json":"https://pith.science/api/pith-number/WVOV2DCN2WEHLGD6DE7EMMPGLR/events.json","paper":"https://pith.science/paper/WVOV2DCN"},"agent_actions":{"view_html":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR","download_json":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR.json","view_paper":"https://pith.science/paper/WVOV2DCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.02042&json=true","fetch_graph":"https://pith.science/api/pith-number/WVOV2DCN2WEHLGD6DE7EMMPGLR/graph.json","fetch_events":"https://pith.science/api/pith-number/WVOV2DCN2WEHLGD6DE7EMMPGLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR/action/storage_attestation","attest_author":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR/action/author_attestation","sign_citation":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR/action/citation_signature","submit_replication":"https://pith.science/pith/WVOV2DCN2WEHLGD6DE7EMMPGLR/action/replication_record"}},"created_at":"2026-07-05T11:18:37.924266+00:00","updated_at":"2026-07-05T11:18:37.924266+00:00"}