{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XH6RPQ4PETY6VL4PT6SZCMABGW","short_pith_number":"pith:XH6RPQ4P","schema_version":"1.0","canonical_sha256":"b9fd17c38f24f1eaaf8f9fa5913001359105a9ef44a889edeaa74cb9f2a0142b","source":{"kind":"arxiv","id":"2202.06053","version":2},"attestation_state":"computed","paper":{"title":"Local Differential Privacy for Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Dongxi Liu, Ibrahim Khalil, M.A.P. Chamikara, Marthie Grobler, Peter Bertok, Seyit Camtepe, Surya Nepal","submitted_at":"2022-02-12T12:40:47Z","abstract_excerpt":"Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially private (DP) solutions. However, DP approaches assume that the FL server (that aggregates the models) is honest (run the FL protocol honestly) or semi-honest (run the FL protocol honestly while also trying to learn as much information as possible). T"},"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":"2202.06053","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2022-02-12T12:40:47Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"8ff30f3a1dd557e8b09513cb5ba4a0edf99b79de94314c3e920e4ff936cdc04b","abstract_canon_sha256":"832e40dc5e0cb64054e59efae2701160278000048649f6fcd0d0657244dba50b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:48.072891Z","signature_b64":"9TEYZmqycAJRZhac3d9cRdXDjFpmkT57zPqmwzCPj+St46ywzy0q9LibzrZ3K1CPu19XfcRQPc0ZfoQlVNIbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9fd17c38f24f1eaaf8f9fa5913001359105a9ef44a889edeaa74cb9f2a0142b","last_reissued_at":"2026-07-05T04:45:48.072471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:48.072471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Differential Privacy for Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CR","authors_text":"Dongxi Liu, Ibrahim Khalil, M.A.P. Chamikara, Marthie Grobler, Peter Bertok, Seyit Camtepe, Surya Nepal","submitted_at":"2022-02-12T12:40:47Z","abstract_excerpt":"Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially private (DP) solutions. However, DP approaches assume that the FL server (that aggregates the models) is honest (run the FL protocol honestly) or semi-honest (run the FL protocol honestly while also trying to learn as much information as possible). T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06053","kind":"arxiv","version":2},"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/2202.06053/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":"2202.06053","created_at":"2026-07-05T04:45:48.072527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06053v2","created_at":"2026-07-05T04:45:48.072527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06053","created_at":"2026-07-05T04:45:48.072527+00:00"},{"alias_kind":"pith_short_12","alias_value":"XH6RPQ4PETY6","created_at":"2026-07-05T04:45:48.072527+00:00"},{"alias_kind":"pith_short_16","alias_value":"XH6RPQ4PETY6VL4P","created_at":"2026-07-05T04:45:48.072527+00:00"},{"alias_kind":"pith_short_8","alias_value":"XH6RPQ4P","created_at":"2026-07-05T04:45:48.072527+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.18809","citing_title":"FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW","json":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW.json","graph_json":"https://pith.science/api/pith-number/XH6RPQ4PETY6VL4PT6SZCMABGW/graph.json","events_json":"https://pith.science/api/pith-number/XH6RPQ4PETY6VL4PT6SZCMABGW/events.json","paper":"https://pith.science/paper/XH6RPQ4P"},"agent_actions":{"view_html":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW","download_json":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW.json","view_paper":"https://pith.science/paper/XH6RPQ4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06053&json=true","fetch_graph":"https://pith.science/api/pith-number/XH6RPQ4PETY6VL4PT6SZCMABGW/graph.json","fetch_events":"https://pith.science/api/pith-number/XH6RPQ4PETY6VL4PT6SZCMABGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW/action/storage_attestation","attest_author":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW/action/author_attestation","sign_citation":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW/action/citation_signature","submit_replication":"https://pith.science/pith/XH6RPQ4PETY6VL4PT6SZCMABGW/action/replication_record"}},"created_at":"2026-07-05T04:45:48.072527+00:00","updated_at":"2026-07-05T04:45:48.072527+00:00"}