{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IXH5TVEGHSCLERJIPLN2U2VFP3","short_pith_number":"pith:IXH5TVEG","schema_version":"1.0","canonical_sha256":"45cfd9d4863c84b245287adbaa6aa57ef195ad6558e998c5af2366dc0ff34a01","source":{"kind":"arxiv","id":"2506.17292","version":2},"attestation_state":"computed","paper":{"title":"Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Minh N. Vu, My T. Thai, Quan Nguyen, Truc Nguyen","submitted_at":"2025-06-16T21:48:11Z","abstract_excerpt":"Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks (MIAs) have challenged this notion, showing high success rates against unprotected training data. While local differential privacy (LDP) is widely regarded as a gold standard for privacy protection in data analysis, most studies on MIAs either neglect LDP or fail to provide theoretical guarantees for attack success rates against LDP-protected data. To address this "},"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":"2506.17292","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-16T21:48:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d33e5d1b15877f2fad057a5ad3454fe6dfa3807916dc9be93e571ac9f4eae7f6","abstract_canon_sha256":"5829b9ad26b41ff340418df39768d6f5c9b6a9da9a090d4e40ac1fbad39f1c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:44.265197Z","signature_b64":"iOkT/BCvXAgw6P56crAY4WjOuINTxseUnhZqUij6pWruKBIL4hapxUmPPOMizKjiRP0CVrz1SrM3TpEbdc6dAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45cfd9d4863c84b245287adbaa6aa57ef195ad6558e998c5af2366dc0ff34a01","last_reissued_at":"2026-07-05T11:46:44.264706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:44.264706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Minh N. Vu, My T. Thai, Quan Nguyen, Truc Nguyen","submitted_at":"2025-06-16T21:48:11Z","abstract_excerpt":"Federated Learning enables collaborative learning among clients via a coordinating server while avoiding direct data sharing, offering a perceived solution to preserve privacy. However, recent studies on Membership Inference Attacks (MIAs) have challenged this notion, showing high success rates against unprotected training data. While local differential privacy (LDP) is widely regarded as a gold standard for privacy protection in data analysis, most studies on MIAs either neglect LDP or fail to provide theoretical guarantees for attack success rates against LDP-protected data. To address this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17292","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/2506.17292/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":"2506.17292","created_at":"2026-07-05T11:46:44.264765+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17292v2","created_at":"2026-07-05T11:46:44.264765+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17292","created_at":"2026-07-05T11:46:44.264765+00:00"},{"alias_kind":"pith_short_12","alias_value":"IXH5TVEGHSCL","created_at":"2026-07-05T11:46:44.264765+00:00"},{"alias_kind":"pith_short_16","alias_value":"IXH5TVEGHSCLERJI","created_at":"2026-07-05T11:46:44.264765+00:00"},{"alias_kind":"pith_short_8","alias_value":"IXH5TVEG","created_at":"2026-07-05T11:46:44.264765+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/IXH5TVEGHSCLERJIPLN2U2VFP3","json":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3.json","graph_json":"https://pith.science/api/pith-number/IXH5TVEGHSCLERJIPLN2U2VFP3/graph.json","events_json":"https://pith.science/api/pith-number/IXH5TVEGHSCLERJIPLN2U2VFP3/events.json","paper":"https://pith.science/paper/IXH5TVEG"},"agent_actions":{"view_html":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3","download_json":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3.json","view_paper":"https://pith.science/paper/IXH5TVEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17292&json=true","fetch_graph":"https://pith.science/api/pith-number/IXH5TVEGHSCLERJIPLN2U2VFP3/graph.json","fetch_events":"https://pith.science/api/pith-number/IXH5TVEGHSCLERJIPLN2U2VFP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3/action/storage_attestation","attest_author":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3/action/author_attestation","sign_citation":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3/action/citation_signature","submit_replication":"https://pith.science/pith/IXH5TVEGHSCLERJIPLN2U2VFP3/action/replication_record"}},"created_at":"2026-07-05T11:46:44.264765+00:00","updated_at":"2026-07-05T11:46:44.264765+00:00"}