{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZFJ2DMLIE4UJNNBUZQPRJLWL4P","short_pith_number":"pith:ZFJ2DMLI","schema_version":"1.0","canonical_sha256":"c953a1b168272896b434cc1f14aecbe3cbe93f3554b4dd2f633b20277d9eb8cd","source":{"kind":"arxiv","id":"2112.02797","version":1},"attestation_state":"computed","paper":{"title":"ML Attack Models: Adversarial Attacks and Data Poisoning Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jing Lin, Kaiqi Xiong, Long Dang, Mohamed Rahouti","submitted_at":"2021-12-06T05:59:30Z","abstract_excerpt":"Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considera"},"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":"2112.02797","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-06T05:59:30Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"6e38854c44daae38c963f4bd18d3c6b7499916875a5f4f849e7585eda4f332ab","abstract_canon_sha256":"295be34cca2ec352dc3b86432fd9752d04c83a69acf189266419478a712a4636"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:57.863067Z","signature_b64":"2uf93dD7heRdZgZGFQErDHJko4fHqBOYkQCgeOEhxY99Qv5yEYxaGERmr7/7r8sWiibraBFY8STCHONPLdsiAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c953a1b168272896b434cc1f14aecbe3cbe93f3554b4dd2f633b20277d9eb8cd","last_reissued_at":"2026-07-05T03:37:57.862546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:57.862546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ML Attack Models: Adversarial Attacks and Data Poisoning Attacks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Jing Lin, Kaiqi Xiong, Long Dang, Mohamed Rahouti","submitted_at":"2021-12-06T05:59:30Z","abstract_excerpt":"Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02797","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/2112.02797/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":"2112.02797","created_at":"2026-07-05T03:37:57.862606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02797v1","created_at":"2026-07-05T03:37:57.862606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02797","created_at":"2026-07-05T03:37:57.862606+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFJ2DMLIE4UJ","created_at":"2026-07-05T03:37:57.862606+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFJ2DMLIE4UJNNBU","created_at":"2026-07-05T03:37:57.862606+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFJ2DMLI","created_at":"2026-07-05T03:37:57.862606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04753","citing_title":"Comparative Insights on Adversarial Machine Learning from Industry and Academia: A User-Study Approach","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12792","citing_title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P","json":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P.json","graph_json":"https://pith.science/api/pith-number/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/graph.json","events_json":"https://pith.science/api/pith-number/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/events.json","paper":"https://pith.science/paper/ZFJ2DMLI"},"agent_actions":{"view_html":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P","download_json":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P.json","view_paper":"https://pith.science/paper/ZFJ2DMLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02797&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/action/storage_attestation","attest_author":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/action/author_attestation","sign_citation":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/action/citation_signature","submit_replication":"https://pith.science/pith/ZFJ2DMLIE4UJNNBUZQPRJLWL4P/action/replication_record"}},"created_at":"2026-07-05T03:37:57.862606+00:00","updated_at":"2026-07-05T03:37:57.862606+00:00"}