{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GMJVRJEA4UTI5MV5LJOFHJHNWO","short_pith_number":"pith:GMJVRJEA","schema_version":"1.0","canonical_sha256":"331358a480e5268eb2bd5a5c53a4edb39e6724f26a42ceb40e4e2592b96b5df4","source":{"kind":"arxiv","id":"2105.10051","version":1},"attestation_state":"computed","paper":{"title":"Preventing Machine Learning Poisoning Attacks Using Authentication and Provenance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jack W. Stokes, Kevin Kane, Paul England","submitted_at":"2021-05-20T21:57:32Z","abstract_excerpt":"Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to identify such attacks. In this work, we take a different approach to preventing data poisoning attacks which relies on cryptographically-based authentication and provenance to ensure the integrity of the data used to train a machine learning model. The same approach is also used to prevent software poisoning and model poisoning attacks. A software poisoning"},"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":"2105.10051","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-05-20T21:57:32Z","cross_cats_sorted":[],"title_canon_sha256":"61fa0c22ffafd2bbcb030cbaa48779d76d63cbbd640a7154ff49baa9adeab5f6","abstract_canon_sha256":"16d4a3a36b59ac5ad308fee71e41f0124e75bc8ee85dc7fba36ccd82c6b43a90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:06.930184Z","signature_b64":"5DbdpbHgbIn0WaEvBeOJ8H36UJTz4jCB1lDqcWrNQ1iCsBovVSKajyjvblPh74VxCY7osO/L1ZTa4ibnfsSHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"331358a480e5268eb2bd5a5c53a4edb39e6724f26a42ceb40e4e2592b96b5df4","last_reissued_at":"2026-07-05T02:42:06.929776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:06.929776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preventing Machine Learning Poisoning Attacks Using Authentication and Provenance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Jack W. Stokes, Kevin Kane, Paul England","submitted_at":"2021-05-20T21:57:32Z","abstract_excerpt":"Recent research has successfully demonstrated new types of data poisoning attacks. To address this problem, some researchers have proposed both offline and online data poisoning detection defenses which employ machine learning algorithms to identify such attacks. In this work, we take a different approach to preventing data poisoning attacks which relies on cryptographically-based authentication and provenance to ensure the integrity of the data used to train a machine learning model. The same approach is also used to prevent software poisoning and model poisoning attacks. A software poisoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.10051","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/2105.10051/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":"2105.10051","created_at":"2026-07-05T02:42:06.929833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.10051v1","created_at":"2026-07-05T02:42:06.929833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.10051","created_at":"2026-07-05T02:42:06.929833+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMJVRJEA4UTI","created_at":"2026-07-05T02:42:06.929833+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMJVRJEA4UTI5MV5","created_at":"2026-07-05T02:42:06.929833+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMJVRJEA","created_at":"2026-07-05T02:42:06.929833+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/GMJVRJEA4UTI5MV5LJOFHJHNWO","json":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO.json","graph_json":"https://pith.science/api/pith-number/GMJVRJEA4UTI5MV5LJOFHJHNWO/graph.json","events_json":"https://pith.science/api/pith-number/GMJVRJEA4UTI5MV5LJOFHJHNWO/events.json","paper":"https://pith.science/paper/GMJVRJEA"},"agent_actions":{"view_html":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO","download_json":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO.json","view_paper":"https://pith.science/paper/GMJVRJEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.10051&json=true","fetch_graph":"https://pith.science/api/pith-number/GMJVRJEA4UTI5MV5LJOFHJHNWO/graph.json","fetch_events":"https://pith.science/api/pith-number/GMJVRJEA4UTI5MV5LJOFHJHNWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO/action/storage_attestation","attest_author":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO/action/author_attestation","sign_citation":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO/action/citation_signature","submit_replication":"https://pith.science/pith/GMJVRJEA4UTI5MV5LJOFHJHNWO/action/replication_record"}},"created_at":"2026-07-05T02:42:06.929833+00:00","updated_at":"2026-07-05T02:42:06.929833+00:00"}