{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HDOTQ3Z3VFKZJYWQWLUHQ2AWQG","short_pith_number":"pith:HDOTQ3Z3","schema_version":"1.0","canonical_sha256":"38dd386f3ba95594e2d0b2e878681681a7925f1c4ac803b164c3461492d61e9f","source":{"kind":"arxiv","id":"2211.06582","version":1},"attestation_state":"computed","paper":{"title":"Provable Membership Inference Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Jinsung Yoon, Sercan O. Arik, Zachary Izzo","submitted_at":"2022-11-12T06:13:00Z","abstract_excerpt":"In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DP's strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning, and DP guarantees themselves can be difficult to interpret. In this work, we propose a novel privacy notion, membership inference privacy (MIP), to address these challenges. We give a precise characterization o"},"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":"2211.06582","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T06:13:00Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"9a7b6d8eb9de75bb76d4c1bbf702e7b470efa4f827767013a78bbae7c1063018","abstract_canon_sha256":"15fd46104fe90b787dbdc7218faf7ff68019a71cf8b980b818fe0a2d27d36802"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:26.602798Z","signature_b64":"gHLh2IC/ggtVF7m1rZexhURBhiNVDCEhB0Jrx0Khj+0KpOcifaT2ym3Gefbal5JvuVjUpk7fYIW6Y3sp17gyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38dd386f3ba95594e2d0b2e878681681a7925f1c4ac803b164c3461492d61e9f","last_reissued_at":"2026-07-05T05:15:26.602418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:26.602418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Membership Inference Privacy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"James Zou, Jinsung Yoon, Sercan O. Arik, Zachary Izzo","submitted_at":"2022-11-12T06:13:00Z","abstract_excerpt":"In applications involving sensitive data, such as finance and healthcare, the necessity for preserving data privacy can be a significant barrier to machine learning model development. Differential privacy (DP) has emerged as one canonical standard for provable privacy. However, DP's strong theoretical guarantees often come at the cost of a large drop in its utility for machine learning, and DP guarantees themselves can be difficult to interpret. In this work, we propose a novel privacy notion, membership inference privacy (MIP), to address these challenges. We give a precise characterization o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06582","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/2211.06582/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":"2211.06582","created_at":"2026-07-05T05:15:26.602471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06582v1","created_at":"2026-07-05T05:15:26.602471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06582","created_at":"2026-07-05T05:15:26.602471+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDOTQ3Z3VFKZ","created_at":"2026-07-05T05:15:26.602471+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDOTQ3Z3VFKZJYWQ","created_at":"2026-07-05T05:15:26.602471+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDOTQ3Z3","created_at":"2026-07-05T05:15:26.602471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19360","citing_title":"SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG","json":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG.json","graph_json":"https://pith.science/api/pith-number/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/graph.json","events_json":"https://pith.science/api/pith-number/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/events.json","paper":"https://pith.science/paper/HDOTQ3Z3"},"agent_actions":{"view_html":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG","download_json":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG.json","view_paper":"https://pith.science/paper/HDOTQ3Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06582&json=true","fetch_graph":"https://pith.science/api/pith-number/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/graph.json","fetch_events":"https://pith.science/api/pith-number/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/action/storage_attestation","attest_author":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/action/author_attestation","sign_citation":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/action/citation_signature","submit_replication":"https://pith.science/pith/HDOTQ3Z3VFKZJYWQWLUHQ2AWQG/action/replication_record"}},"created_at":"2026-07-05T05:15:26.602471+00:00","updated_at":"2026-07-05T05:15:26.602471+00:00"}