{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U7TRZXSYODOSCT7WXCGFZISMH2","short_pith_number":"pith:U7TRZXSY","schema_version":"1.0","canonical_sha256":"a7e71cde5870dd214ff6b88c5ca24c3eb52da0b375bb742d74608b2103c1d90a","source":{"kind":"arxiv","id":"2107.01614","version":2},"attestation_state":"computed","paper":{"title":"Survey: Leakage and Privacy at Inference Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Weir, Alison Q. O'Neil, Chaitanya Kaul, Charlie Mayor, Marija Jegorova, Roderick Murray-Smith, Sotirios A. Tsaftaris","submitted_at":"2021-07-04T12:59:16Z","abstract_excerpt":"Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of contemporary advances on several fronts, covering involuntary data leakage which is natural to ML models, potential malevolent leakage which is caused by privacy attacks, and currently available defence mechanisms. We focus on inference-time leakage, as the most likely scenario for publicly available models. We fi"},"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":"2107.01614","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-04T12:59:16Z","cross_cats_sorted":[],"title_canon_sha256":"fb651ee8458305ad3016f057fd788e9ad755d98577f21727ac57b37f2d895283","abstract_canon_sha256":"be9a05ea650e6af63f87e4a473798e4c6fe4a06bd17a1539b5ef09e0e0a734fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:48.956941Z","signature_b64":"DsKljsVwxTwCuDxjvRjcl2sJeKjGgVNxRdiBaY4KYA/c1HCsG1CyzKHmF5hMtNb1HLxKOeZ1RCa7+Aopbx9cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7e71cde5870dd214ff6b88c5ca24c3eb52da0b375bb742d74608b2103c1d90a","last_reissued_at":"2026-07-05T04:55:48.956528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:48.956528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Survey: Leakage and Privacy at Inference Time","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Weir, Alison Q. O'Neil, Chaitanya Kaul, Charlie Mayor, Marija Jegorova, Roderick Murray-Smith, Sotirios A. Tsaftaris","submitted_at":"2021-07-04T12:59:16Z","abstract_excerpt":"Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance as commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of contemporary advances on several fronts, covering involuntary data leakage which is natural to ML models, potential malevolent leakage which is caused by privacy attacks, and currently available defence mechanisms. We focus on inference-time leakage, as the most likely scenario for publicly available models. We fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01614","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/2107.01614/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":"2107.01614","created_at":"2026-07-05T04:55:48.956583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01614v2","created_at":"2026-07-05T04:55:48.956583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01614","created_at":"2026-07-05T04:55:48.956583+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7TRZXSYODOS","created_at":"2026-07-05T04:55:48.956583+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7TRZXSYODOSCT7W","created_at":"2026-07-05T04:55:48.956583+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7TRZXSY","created_at":"2026-07-05T04:55:48.956583+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/U7TRZXSYODOSCT7WXCGFZISMH2","json":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2.json","graph_json":"https://pith.science/api/pith-number/U7TRZXSYODOSCT7WXCGFZISMH2/graph.json","events_json":"https://pith.science/api/pith-number/U7TRZXSYODOSCT7WXCGFZISMH2/events.json","paper":"https://pith.science/paper/U7TRZXSY"},"agent_actions":{"view_html":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2","download_json":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2.json","view_paper":"https://pith.science/paper/U7TRZXSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01614&json=true","fetch_graph":"https://pith.science/api/pith-number/U7TRZXSYODOSCT7WXCGFZISMH2/graph.json","fetch_events":"https://pith.science/api/pith-number/U7TRZXSYODOSCT7WXCGFZISMH2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2/action/storage_attestation","attest_author":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2/action/author_attestation","sign_citation":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2/action/citation_signature","submit_replication":"https://pith.science/pith/U7TRZXSYODOSCT7WXCGFZISMH2/action/replication_record"}},"created_at":"2026-07-05T04:55:48.956583+00:00","updated_at":"2026-07-05T04:55:48.956583+00:00"}