{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2U6KPEBJOQF66SQAGTP3OOU5BI","short_pith_number":"pith:2U6KPEBJ","schema_version":"1.0","canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","source":{"kind":"arxiv","id":"1808.05760","version":2},"attestation_state":"computed","paper":{"title":"Data Poisoning Attacks in Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kwang-Sung Jun, Lihong Li, Xiaojin Zhu, Yuzhe Ma","submitted_at":"2018-08-17T05:25:29Z","abstract_excerpt":"We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the f"},"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":"1808.05760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-17T05:25:29Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"7c80a2f16afa28b67fcc3bab0d3871a0548b3260d1f71ef93cd3c9ea94f990db","abstract_canon_sha256":"eb8e68e2457e468f8a55c4c61545cd2c24a3e46ace99c8072750b19a2faeaedd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:23.157467Z","signature_b64":"XAetEPdxAwJKj5tJ34/u28vpSoazOGxmWbNEFfjRzvFO2Hfr1ZK7l25AhGECz51PCpvvqDN/WUR+2XI6IpteBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d53ca79029740bef4a0034dfb73a9d0a3244a7a83dfec845abb59a40f40f9343","last_reissued_at":"2026-05-18T00:07:23.156944Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:23.156944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Poisoning Attacks in Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kwang-Sung Jun, Lihong Li, Xiaojin Zhu, Yuzhe Ma","submitted_at":"2018-08-17T05:25:29Z","abstract_excerpt":"We study offline data poisoning attacks in contextual bandits, a class of reinforcement learning problems with important applications in online recommendation and adaptive medical treatment, among others. We provide a general attack framework based on convex optimization and show that by slightly manipulating rewards in the data, an attacker can force the bandit algorithm to pull a target arm for a target contextual vector. The target arm and target contextual vector are both chosen by the attacker. That is, the attacker can hijack the behavior of a contextual bandit. We also investigate the f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.05760","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":""},"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":"1808.05760","created_at":"2026-05-18T00:07:23.157027+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.05760v2","created_at":"2026-05-18T00:07:23.157027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.05760","created_at":"2026-05-18T00:07:23.157027+00:00"},{"alias_kind":"pith_short_12","alias_value":"2U6KPEBJOQF6","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2U6KPEBJOQF66SQA","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2U6KPEBJ","created_at":"2026-05-18T12:32:02.567920+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/2U6KPEBJOQF66SQAGTP3OOU5BI","json":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI.json","graph_json":"https://pith.science/api/pith-number/2U6KPEBJOQF66SQAGTP3OOU5BI/graph.json","events_json":"https://pith.science/api/pith-number/2U6KPEBJOQF66SQAGTP3OOU5BI/events.json","paper":"https://pith.science/paper/2U6KPEBJ"},"agent_actions":{"view_html":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI","download_json":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI.json","view_paper":"https://pith.science/paper/2U6KPEBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.05760&json=true","fetch_graph":"https://pith.science/api/pith-number/2U6KPEBJOQF66SQAGTP3OOU5BI/graph.json","fetch_events":"https://pith.science/api/pith-number/2U6KPEBJOQF66SQAGTP3OOU5BI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/action/storage_attestation","attest_author":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/action/author_attestation","sign_citation":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/action/citation_signature","submit_replication":"https://pith.science/pith/2U6KPEBJOQF66SQAGTP3OOU5BI/action/replication_record"}},"created_at":"2026-05-18T00:07:23.157027+00:00","updated_at":"2026-05-18T00:07:23.157027+00:00"}