{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4IGCN5AVXND6ITZWBVR6BYLV5","short_pith_number":"pith:D4IGCN5A","schema_version":"1.0","canonical_sha256":"1f106137a0adda3f2279b06b1f070baf6076fc2cde93b97eabbf31a7d5dbc7e1","source":{"kind":"arxiv","id":"2404.09724","version":1},"attestation_state":"computed","paper":{"title":"Privacy-Preserving Federated Unlearning with Certified Client Removal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Huanyi Ye, Ivan Tjuawinata, Jiale Guo, Jiyuan Shen, Kwok-Yan Lam, Yu Jiang, Ziyao Liu","submitted_at":"2024-04-15T12:27:07Z","abstract_excerpt":"In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client's influence from the global model in Federated Learning (FL) systems, thereby ensuring the ``right to be forgotten\" (RTBF). State-of-the-art methods for unlearning use historical data from FL clients, such as gradients or locally trained models. However, studies have revealed significant information leakage in this setting, with the possibility of reconstructing a user's local data from their uploaded information. Addressing this, we propose Starfish, a privacy-preserving federated unlearning"},"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":"2404.09724","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-04-15T12:27:07Z","cross_cats_sorted":[],"title_canon_sha256":"cca647e85a4354605699156e7532a0a6fd0bcc95489b34b604ba6ac295f041f5","abstract_canon_sha256":"0f18139cd44f6c412b050de3585ffdbe836e4d02c7f85276fe9916f5e857ef73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:10.961013Z","signature_b64":"YGEgPR3fZrN9v2bmRsoPTzy8HGG6KcTFXE0r4TQE6tEj8InL/vpR3MCXxyq97zfy6RVKviO0jkV/WYu0RBJGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f106137a0adda3f2279b06b1f070baf6076fc2cde93b97eabbf31a7d5dbc7e1","last_reissued_at":"2026-07-05T08:08:10.960544Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:10.960544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy-Preserving Federated Unlearning with Certified Client Removal","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Huanyi Ye, Ivan Tjuawinata, Jiale Guo, Jiyuan Shen, Kwok-Yan Lam, Yu Jiang, Ziyao Liu","submitted_at":"2024-04-15T12:27:07Z","abstract_excerpt":"In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client's influence from the global model in Federated Learning (FL) systems, thereby ensuring the ``right to be forgotten\" (RTBF). State-of-the-art methods for unlearning use historical data from FL clients, such as gradients or locally trained models. However, studies have revealed significant information leakage in this setting, with the possibility of reconstructing a user's local data from their uploaded information. Addressing this, we propose Starfish, a privacy-preserving federated unlearning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09724","kind":"arxiv","version":1},"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/2404.09724/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":"2404.09724","created_at":"2026-07-05T08:08:10.960618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.09724v1","created_at":"2026-07-05T08:08:10.960618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09724","created_at":"2026-07-05T08:08:10.960618+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4IGCN5AVXND","created_at":"2026-07-05T08:08:10.960618+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4IGCN5AVXND6ITZ","created_at":"2026-07-05T08:08:10.960618+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4IGCN5A","created_at":"2026-07-05T08:08:10.960618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5","json":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5.json","graph_json":"https://pith.science/api/pith-number/D4IGCN5AVXND6ITZWBVR6BYLV5/graph.json","events_json":"https://pith.science/api/pith-number/D4IGCN5AVXND6ITZWBVR6BYLV5/events.json","paper":"https://pith.science/paper/D4IGCN5A"},"agent_actions":{"view_html":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5","download_json":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5.json","view_paper":"https://pith.science/paper/D4IGCN5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.09724&json=true","fetch_graph":"https://pith.science/api/pith-number/D4IGCN5AVXND6ITZWBVR6BYLV5/graph.json","fetch_events":"https://pith.science/api/pith-number/D4IGCN5AVXND6ITZWBVR6BYLV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5/action/storage_attestation","attest_author":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5/action/author_attestation","sign_citation":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5/action/citation_signature","submit_replication":"https://pith.science/pith/D4IGCN5AVXND6ITZWBVR6BYLV5/action/replication_record"}},"created_at":"2026-07-05T08:08:10.960618+00:00","updated_at":"2026-07-05T08:08:10.960618+00:00"}