{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEGLREU5254J3P25HBOMDGXBPV","short_pith_number":"pith:YEGLREU5","schema_version":"1.0","canonical_sha256":"c10cb8929dd7789dbf5d385cc19ae17d66bf93fe3d361420cb46faf02afabc7a","source":{"kind":"arxiv","id":"2404.00696","version":1},"attestation_state":"computed","paper":{"title":"Privacy Re-identification Attacks on Tabular GANs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Abdallah Alshantti, Adil Rasheed, Frank Westad","submitted_at":"2024-03-31T14:14:00Z","abstract_excerpt":"Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial networks (GANs) for creating tabular synthetic datasets. For the purpose, we analyse the effects of re-identification attacks on synthetic data, i.e., attacks which aim at selecting samples that are predicted to correspond to memorised training samples based on their proximity to the nearest synthetic records. We thus consider multiple settings where different att"},"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":"2404.00696","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-03-31T14:14:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"664608ef25b28d9e2fb28a1d4cb52637198f63bc74cd8969d577b30202ecd772","abstract_canon_sha256":"64350ca95a912689f37f2384d7929158ea07488417dd3d9be21bd72dba7e1694"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:55.482853Z","signature_b64":"SpqhYrXo+lKfzWRaPYQfpq0LKJ1C6hoA5JKAXGeUWw6PbCYNP0Us87tUK9Bfd4Vlzp4/LLiiAPLe+JQ2KjeTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10cb8929dd7789dbf5d385cc19ae17d66bf93fe3d361420cb46faf02afabc7a","last_reissued_at":"2026-07-05T08:02:55.482393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:55.482393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Privacy Re-identification Attacks on Tabular GANs","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Abdallah Alshantti, Adil Rasheed, Frank Westad","submitted_at":"2024-03-31T14:14:00Z","abstract_excerpt":"Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial networks (GANs) for creating tabular synthetic datasets. For the purpose, we analyse the effects of re-identification attacks on synthetic data, i.e., attacks which aim at selecting samples that are predicted to correspond to memorised training samples based on their proximity to the nearest synthetic records. We thus consider multiple settings where different att"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00696","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/2404.00696/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":"2404.00696","created_at":"2026-07-05T08:02:55.482468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.00696v1","created_at":"2026-07-05T08:02:55.482468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00696","created_at":"2026-07-05T08:02:55.482468+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEGLREU5254J","created_at":"2026-07-05T08:02:55.482468+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEGLREU5254J3P25","created_at":"2026-07-05T08:02:55.482468+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEGLREU5","created_at":"2026-07-05T08:02:55.482468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.02947","citing_title":"Quality Degradation Attack in Synthetic Data","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV","json":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV.json","graph_json":"https://pith.science/api/pith-number/YEGLREU5254J3P25HBOMDGXBPV/graph.json","events_json":"https://pith.science/api/pith-number/YEGLREU5254J3P25HBOMDGXBPV/events.json","paper":"https://pith.science/paper/YEGLREU5"},"agent_actions":{"view_html":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV","download_json":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV.json","view_paper":"https://pith.science/paper/YEGLREU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.00696&json=true","fetch_graph":"https://pith.science/api/pith-number/YEGLREU5254J3P25HBOMDGXBPV/graph.json","fetch_events":"https://pith.science/api/pith-number/YEGLREU5254J3P25HBOMDGXBPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV/action/storage_attestation","attest_author":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV/action/author_attestation","sign_citation":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV/action/citation_signature","submit_replication":"https://pith.science/pith/YEGLREU5254J3P25HBOMDGXBPV/action/replication_record"}},"created_at":"2026-07-05T08:02:55.482468+00:00","updated_at":"2026-07-05T08:02:55.482468+00:00"}