{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CQJ4YUDCRMDMIG3Z6METRCP2HJ","short_pith_number":"pith:CQJ4YUDC","schema_version":"1.0","canonical_sha256":"1413cc50628b06c41b79f3093889fa3a4a1840de1e075fd253058e6dec9f79ea","source":{"kind":"arxiv","id":"2210.10750","version":2},"attestation_state":"computed","paper":{"title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Arpit Bansal, Eitan Borgnia, Hamid Kazemi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Yuxin Wen","submitted_at":"2022-10-19T17:46:50Z","abstract_excerpt":"As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to discern whether a target sample was included in a model's training set. However, existing methods only utilize the unaltered target sample or simple augmentations of the target to compute statistics. Such a sparse sampling of the model's behavior carries little information, leading to poor inference"},"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":"2210.10750","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-19T17:46:50Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"9cf3d4fb76204f7d8892c8ee35d0b2c434451dc1bb1e61303cfaebafc80b5f68","abstract_canon_sha256":"c96eea895e2439a4739644535261e7c222ade5ce7c05a1de0c599648663ddbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:12.802377Z","signature_b64":"59oUuyVc5l2L8WYdS4mXhygqWQCJvkTnNKAih407A5Osl3l/q3U5lzhPPZyRkuh5cH368hU9Pc9i5kegInPKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1413cc50628b06c41b79f3093889fa3a4a1840de1e075fd253058e6dec9f79ea","last_reissued_at":"2026-07-05T06:16:12.801859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:12.801859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Arpit Bansal, Eitan Borgnia, Hamid Kazemi, Jonas Geiping, Micah Goldblum, Tom Goldstein, Yuxin Wen","submitted_at":"2022-10-19T17:46:50Z","abstract_excerpt":"As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to discern whether a target sample was included in a model's training set. However, existing methods only utilize the unaltered target sample or simple augmentations of the target to compute statistics. Such a sparse sampling of the model's behavior carries little information, leading to poor inference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10750","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/2210.10750/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":"2210.10750","created_at":"2026-07-05T06:16:12.801916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10750v2","created_at":"2026-07-05T06:16:12.801916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10750","created_at":"2026-07-05T06:16:12.801916+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQJ4YUDCRMDM","created_at":"2026-07-05T06:16:12.801916+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQJ4YUDCRMDMIG3Z","created_at":"2026-07-05T06:16:12.801916+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQJ4YUDC","created_at":"2026-07-05T06:16:12.801916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01129","citing_title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01129","citing_title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ","json":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ.json","graph_json":"https://pith.science/api/pith-number/CQJ4YUDCRMDMIG3Z6METRCP2HJ/graph.json","events_json":"https://pith.science/api/pith-number/CQJ4YUDCRMDMIG3Z6METRCP2HJ/events.json","paper":"https://pith.science/paper/CQJ4YUDC"},"agent_actions":{"view_html":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ","download_json":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ.json","view_paper":"https://pith.science/paper/CQJ4YUDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10750&json=true","fetch_graph":"https://pith.science/api/pith-number/CQJ4YUDCRMDMIG3Z6METRCP2HJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CQJ4YUDCRMDMIG3Z6METRCP2HJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ/action/storage_attestation","attest_author":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ/action/author_attestation","sign_citation":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ/action/citation_signature","submit_replication":"https://pith.science/pith/CQJ4YUDCRMDMIG3Z6METRCP2HJ/action/replication_record"}},"created_at":"2026-07-05T06:16:12.801916+00:00","updated_at":"2026-07-05T06:16:12.801916+00:00"}