{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6N4BZ4GSLWA4MMT3W3NPLDRHBV","short_pith_number":"pith:6N4BZ4GS","schema_version":"1.0","canonical_sha256":"f3781cf0d25d81c6327bb6daf58e270d4424533fd007d05735f8fae47585bf19","source":{"kind":"arxiv","id":"2305.04095","version":3},"attestation_state":"computed","paper":{"title":"Gradient Leakage Defense with Key-Lock Module for Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hanchi Ren, Jingjing Deng, Xianghua Xie","submitted_at":"2023-05-06T16:47:52Z","abstract_excerpt":"Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party parameter servers. However, recent findings reveal that privacy may be compromised and sensitive information potentially recovered from shared gradients. In this study, we offer detailed analysis and a novel perspective on understanding the gradient leakage problem. These theoretical works lead to a new gradient leakage defense technique that secures arbitrary model"},"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":"2305.04095","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-06T16:47:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c6efb5e5a576af23150014dbad6890aef2585f013e641a051a83c2992f59eaf7","abstract_canon_sha256":"94d22fea934602220fe5d57fb8d6fb49308964f9fe7e0bbbf54fdb57522b0a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:32.977162Z","signature_b64":"gGethSH2UTiKJTRJ3qcoxZ5FVrLHTE14CmpQbdrsFxDmXKuwLRDt0hY6zbUFFwnNkQADWbt8lgj4VMuqxWxQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3781cf0d25d81c6327bb6daf58e270d4424533fd007d05735f8fae47585bf19","last_reissued_at":"2026-07-05T11:46:32.976623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:32.976623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Leakage Defense with Key-Lock Module for Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hanchi Ren, Jingjing Deng, Xianghua Xie","submitted_at":"2023-05-06T16:47:52Z","abstract_excerpt":"Federated Learning (FL) is a widely adopted privacy-preserving machine learning approach where private data remains local, enabling secure computations and the exchange of local model gradients between local clients and third-party parameter servers. However, recent findings reveal that privacy may be compromised and sensitive information potentially recovered from shared gradients. In this study, we offer detailed analysis and a novel perspective on understanding the gradient leakage problem. These theoretical works lead to a new gradient leakage defense technique that secures arbitrary model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04095","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/2305.04095/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":"2305.04095","created_at":"2026-07-05T11:46:32.976701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04095v3","created_at":"2026-07-05T11:46:32.976701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04095","created_at":"2026-07-05T11:46:32.976701+00:00"},{"alias_kind":"pith_short_12","alias_value":"6N4BZ4GSLWA4","created_at":"2026-07-05T11:46:32.976701+00:00"},{"alias_kind":"pith_short_16","alias_value":"6N4BZ4GSLWA4MMT3","created_at":"2026-07-05T11:46:32.976701+00:00"},{"alias_kind":"pith_short_8","alias_value":"6N4BZ4GS","created_at":"2026-07-05T11:46:32.976701+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":109,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV","json":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV.json","graph_json":"https://pith.science/api/pith-number/6N4BZ4GSLWA4MMT3W3NPLDRHBV/graph.json","events_json":"https://pith.science/api/pith-number/6N4BZ4GSLWA4MMT3W3NPLDRHBV/events.json","paper":"https://pith.science/paper/6N4BZ4GS"},"agent_actions":{"view_html":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV","download_json":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV.json","view_paper":"https://pith.science/paper/6N4BZ4GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04095&json=true","fetch_graph":"https://pith.science/api/pith-number/6N4BZ4GSLWA4MMT3W3NPLDRHBV/graph.json","fetch_events":"https://pith.science/api/pith-number/6N4BZ4GSLWA4MMT3W3NPLDRHBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV/action/storage_attestation","attest_author":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV/action/author_attestation","sign_citation":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV/action/citation_signature","submit_replication":"https://pith.science/pith/6N4BZ4GSLWA4MMT3W3NPLDRHBV/action/replication_record"}},"created_at":"2026-07-05T11:46:32.976701+00:00","updated_at":"2026-07-05T11:46:32.976701+00:00"}