{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FVIEL2D7E75GKIICCXUKCRW33R","short_pith_number":"pith:FVIEL2D7","schema_version":"1.0","canonical_sha256":"2d5045e87f27fa65210215e8a146dbdc5e42010c0b8dab05d32f79a0bb5cb619","source":{"kind":"arxiv","id":"1912.01206","version":1},"attestation_state":"computed","paper":{"title":"Deep Probabilistic Models to Detect Data Poisoning Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ibrahima J. Ndiour, Mahesh Subedar, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan","submitted_at":"2019-12-03T05:58:51Z","abstract_excerpt":"Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural networks (DNNs) by inserting a backdoor pattern in the training images. The resulting attack will misclassify poisoned test samples while maintaining high accuracies for the clean test-set. We present two approaches for detection of such poisoned samples by quantifying the uncertainty estimates associated with the trained models. In the first approach, we model t"},"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":"1912.01206","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T05:58:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"de6cc99d872bdde32815d7eb28c3f88c405de5eb53967492b916d72fc7b61bda","abstract_canon_sha256":"c57a1ab180f00f610362b9655980d9df139c17d91a19ed9476d43a8cc512061f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:28.110163Z","signature_b64":"UZALgTkm35TRJg4kWC/xM5em5ebiVvw75rMrD2jtULaPt67Tw/CgH6gurxHuhYrFz4q3tgiTDoGDPmNzdnA0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d5045e87f27fa65210215e8a146dbdc5e42010c0b8dab05d32f79a0bb5cb619","last_reissued_at":"2026-07-05T00:23:28.109732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:28.109732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Probabilistic Models to Detect Data Poisoning Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ibrahima J. Ndiour, Mahesh Subedar, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan","submitted_at":"2019-12-03T05:58:51Z","abstract_excerpt":"Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural networks (DNNs) by inserting a backdoor pattern in the training images. The resulting attack will misclassify poisoned test samples while maintaining high accuracies for the clean test-set. We present two approaches for detection of such poisoned samples by quantifying the uncertainty estimates associated with the trained models. In the first approach, we model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01206","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/1912.01206/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":"1912.01206","created_at":"2026-07-05T00:23:28.109788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01206v1","created_at":"2026-07-05T00:23:28.109788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01206","created_at":"2026-07-05T00:23:28.109788+00:00"},{"alias_kind":"pith_short_12","alias_value":"FVIEL2D7E75G","created_at":"2026-07-05T00:23:28.109788+00:00"},{"alias_kind":"pith_short_16","alias_value":"FVIEL2D7E75GKIIC","created_at":"2026-07-05T00:23:28.109788+00:00"},{"alias_kind":"pith_short_8","alias_value":"FVIEL2D7","created_at":"2026-07-05T00:23:28.109788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.00842","citing_title":"A Survey of Secure Semantic Communications","ref_index":144,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R","json":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R.json","graph_json":"https://pith.science/api/pith-number/FVIEL2D7E75GKIICCXUKCRW33R/graph.json","events_json":"https://pith.science/api/pith-number/FVIEL2D7E75GKIICCXUKCRW33R/events.json","paper":"https://pith.science/paper/FVIEL2D7"},"agent_actions":{"view_html":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R","download_json":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R.json","view_paper":"https://pith.science/paper/FVIEL2D7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01206&json=true","fetch_graph":"https://pith.science/api/pith-number/FVIEL2D7E75GKIICCXUKCRW33R/graph.json","fetch_events":"https://pith.science/api/pith-number/FVIEL2D7E75GKIICCXUKCRW33R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R/action/storage_attestation","attest_author":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R/action/author_attestation","sign_citation":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R/action/citation_signature","submit_replication":"https://pith.science/pith/FVIEL2D7E75GKIICCXUKCRW33R/action/replication_record"}},"created_at":"2026-07-05T00:23:28.109788+00:00","updated_at":"2026-07-05T00:23:28.109788+00:00"}