{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PZKQXEN3426HFIVXCETECLVHX5","short_pith_number":"pith:PZKQXEN3","schema_version":"1.0","canonical_sha256":"7e550b91bbe6bc72a2b71126412ea7bf53f9a7ce1c9e39f84b641a0c54997de3","source":{"kind":"arxiv","id":"2302.12580","version":1},"attestation_state":"computed","paper":{"title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Hao Sun, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-02-24T11:27:39Z","abstract_excerpt":"Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that has the same distribution as the original data, but that does not disclose information about individuals. Membership Inference Attacks (MIAs) are a common privacy attack, in which the attacker attempts to determine whether a particular real sample was used for training of the model. Previous works that propose MIAs against generative models either display lo"},"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":"2302.12580","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T11:27:39Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"4d55f9ce948713a99d687712eeb624a44f0fe3882bab1df7d5b398e37d6d3106","abstract_canon_sha256":"40a66eaa2ee46bcf4e89304f765a25757b8705194e3f0837e2d5fbe2acfa8b70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:11.395951Z","signature_b64":"IF1uV8GpFkuj+jaWBYXxYszrs8d+WNvbFnCY0zrEFwovQ7uk+BYy9S72OMy05yyoqOmjm/49jOc1jqCvdkd4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e550b91bbe6bc72a2b71126412ea7bf53f9a7ce1c9e39f84b641a0c54997de3","last_reissued_at":"2026-07-05T05:45:11.395538Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:11.395538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Membership Inference Attacks against Synthetic Data through Overfitting Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Boris van Breugel, Hao Sun, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2023-02-24T11:27:39Z","abstract_excerpt":"Data is the foundation of most science. Unfortunately, sharing data can be obstructed by the risk of violating data privacy, impeding research in fields like healthcare. Synthetic data is a potential solution. It aims to generate data that has the same distribution as the original data, but that does not disclose information about individuals. Membership Inference Attacks (MIAs) are a common privacy attack, in which the attacker attempts to determine whether a particular real sample was used for training of the model. Previous works that propose MIAs against generative models either display lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12580","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/2302.12580/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":"2302.12580","created_at":"2026-07-05T05:45:11.395599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12580v1","created_at":"2026-07-05T05:45:11.395599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12580","created_at":"2026-07-05T05:45:11.395599+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZKQXEN3426H","created_at":"2026-07-05T05:45:11.395599+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZKQXEN3426HFIVX","created_at":"2026-07-05T05:45:11.395599+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZKQXEN3","created_at":"2026-07-05T05:45:11.395599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08372","citing_title":"SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01785","citing_title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08875","citing_title":"When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11527","citing_title":"FERMI: Exploiting Relations for Membership Inference Against Tabular Diffusion Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19653","citing_title":"A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities","ref_index":118,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5","json":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5.json","graph_json":"https://pith.science/api/pith-number/PZKQXEN3426HFIVXCETECLVHX5/graph.json","events_json":"https://pith.science/api/pith-number/PZKQXEN3426HFIVXCETECLVHX5/events.json","paper":"https://pith.science/paper/PZKQXEN3"},"agent_actions":{"view_html":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5","download_json":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5.json","view_paper":"https://pith.science/paper/PZKQXEN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12580&json=true","fetch_graph":"https://pith.science/api/pith-number/PZKQXEN3426HFIVXCETECLVHX5/graph.json","fetch_events":"https://pith.science/api/pith-number/PZKQXEN3426HFIVXCETECLVHX5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5/action/storage_attestation","attest_author":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5/action/author_attestation","sign_citation":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5/action/citation_signature","submit_replication":"https://pith.science/pith/PZKQXEN3426HFIVXCETECLVHX5/action/replication_record"}},"created_at":"2026-07-05T05:45:11.395599+00:00","updated_at":"2026-07-05T05:45:11.395599+00:00"}