{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DHMGCIGEDKND2SCVJO34UUCNU2","short_pith_number":"pith:DHMGCIGE","schema_version":"1.0","canonical_sha256":"19d86120c41a9a3d48554bb7ca504da6b6a6a44850a54a00b7e1c2200ecd9952","source":{"kind":"arxiv","id":"1906.00389","version":4},"attestation_state":"computed","paper":{"title":"Disparate Vulnerability to Membership Inference Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bogdan Kulynych, Carmela Troncoso, Giovanni Cherubin, Michael Veale, Mohammad Yaghini","submitted_at":"2019-06-02T11:37:00Z","abstract_excerpt":"A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against different population subgroups. We first establish necessary and sufficient conditions for MIAs to be prevented, both on average and for population subgroups, using a notion of distributional generalization. Second, we derive connections of disparate vulnerability to algorithmic fair"},"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":"1906.00389","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-02T11:37:00Z","cross_cats_sorted":["cs.CR","cs.CY","stat.ML"],"title_canon_sha256":"f3ffe496a4aad7e9ba12ec8b52a602a0ce856c17e44bf039425af901613c6766","abstract_canon_sha256":"712d5cd6658094b43773a85ff65ae9a29e25ac300082ab27e55e34bb89fd2d2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:06.353607Z","signature_b64":"u8AKmPzo2z86qekGp416ZOwbWLU3AnzH3gkXblsSV8KqQEbyhr5tM3S96i+lTl3zJgT0wHIUTK/IF07j5M1eCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d86120c41a9a3d48554bb7ca504da6b6a6a44850a54a00b7e1c2200ecd9952","last_reissued_at":"2026-07-05T03:15:06.353141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:06.353141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disparate Vulnerability to Membership Inference Attacks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CR","cs.CY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bogdan Kulynych, Carmela Troncoso, Giovanni Cherubin, Michael Veale, Mohammad Yaghini","submitted_at":"2019-06-02T11:37:00Z","abstract_excerpt":"A membership inference attack (MIA) against a machine-learning model enables an attacker to determine whether a given data record was part of the model's training data or not. In this paper, we provide an in-depth study of the phenomenon of disparate vulnerability against MIAs: unequal success rate of MIAs against different population subgroups. We first establish necessary and sufficient conditions for MIAs to be prevented, both on average and for population subgroups, using a notion of distributional generalization. Second, we derive connections of disparate vulnerability to algorithmic fair"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00389","kind":"arxiv","version":4},"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/1906.00389/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":"1906.00389","created_at":"2026-07-05T03:15:06.353197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00389v4","created_at":"2026-07-05T03:15:06.353197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00389","created_at":"2026-07-05T03:15:06.353197+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHMGCIGEDKND","created_at":"2026-07-05T03:15:06.353197+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHMGCIGEDKND2SCV","created_at":"2026-07-05T03:15:06.353197+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHMGCIGE","created_at":"2026-07-05T03:15:06.353197+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/DHMGCIGEDKND2SCVJO34UUCNU2","json":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2.json","graph_json":"https://pith.science/api/pith-number/DHMGCIGEDKND2SCVJO34UUCNU2/graph.json","events_json":"https://pith.science/api/pith-number/DHMGCIGEDKND2SCVJO34UUCNU2/events.json","paper":"https://pith.science/paper/DHMGCIGE"},"agent_actions":{"view_html":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2","download_json":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2.json","view_paper":"https://pith.science/paper/DHMGCIGE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00389&json=true","fetch_graph":"https://pith.science/api/pith-number/DHMGCIGEDKND2SCVJO34UUCNU2/graph.json","fetch_events":"https://pith.science/api/pith-number/DHMGCIGEDKND2SCVJO34UUCNU2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2/action/storage_attestation","attest_author":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2/action/author_attestation","sign_citation":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2/action/citation_signature","submit_replication":"https://pith.science/pith/DHMGCIGEDKND2SCVJO34UUCNU2/action/replication_record"}},"created_at":"2026-07-05T03:15:06.353197+00:00","updated_at":"2026-07-05T03:15:06.353197+00:00"}