{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KY3EY3H2MTW4L23NC2ZWHATEU7","short_pith_number":"pith:KY3EY3H2","schema_version":"1.0","canonical_sha256":"56364c6cfa64edc5eb6d16b3638264a7f4dd6d46e2a53926759a2dbd50b8f1f0","source":{"kind":"arxiv","id":"2503.01734","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Eric Pauley, Jean-Charles Noirot Ferrand, Josiah Hanna, Kyle Domico, Patrick McDaniel, Ryan Sheatsley","submitted_at":"2025-03-03T16:54:03Z","abstract_excerpt":"Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial samples. Unlike traditional adversarial machine learning (AML) methods that craft adversarial samples independently, our RL-based approach retains and exploits past attack experience to improve the effectiveness and efficiency of future attacks. We formulate adversarial sample generation as a Markov Decision Process and evaluate RL's ability to (a) learn effecti"},"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":"2503.01734","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-03-03T16:54:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71e4fae90b523d720e0cfa941cf87be4865f25287881f128000b5bce8ecccbc8","abstract_canon_sha256":"7e1d2ac94a682eb6c1f4ab9ca192e39db86c1120d5b90c545bd48e3af3c1df7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:43.395669Z","signature_b64":"38pCb819lrlyRnOOayJr/hu+Nxw+5hTHLGafZUX6s5+wTycSBcTy1H7DblD1d9RiICD7oG3tigppuqkzAnF8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56364c6cfa64edc5eb6d16b3638264a7f4dd6d46e2a53926759a2dbd50b8f1f0","last_reissued_at":"2026-06-05T00:13:43.395013Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:43.395013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Eric Pauley, Jean-Charles Noirot Ferrand, Josiah Hanna, Kyle Domico, Patrick McDaniel, Ryan Sheatsley","submitted_at":"2025-03-03T16:54:03Z","abstract_excerpt":"Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a new class of attack algorithms that generate adversarial samples. Unlike traditional adversarial machine learning (AML) methods that craft adversarial samples independently, our RL-based approach retains and exploits past attack experience to improve the effectiveness and efficiency of future attacks. We formulate adversarial sample generation as a Markov Decision Process and evaluate RL's ability to (a) learn effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01734","kind":"arxiv","version":3},"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/2503.01734/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":"2503.01734","created_at":"2026-06-05T00:13:43.395091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01734v3","created_at":"2026-06-05T00:13:43.395091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01734","created_at":"2026-06-05T00:13:43.395091+00:00"},{"alias_kind":"pith_short_12","alias_value":"KY3EY3H2MTW4","created_at":"2026-06-05T00:13:43.395091+00:00"},{"alias_kind":"pith_short_16","alias_value":"KY3EY3H2MTW4L23N","created_at":"2026-06-05T00:13:43.395091+00:00"},{"alias_kind":"pith_short_8","alias_value":"KY3EY3H2","created_at":"2026-06-05T00:13:43.395091+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/KY3EY3H2MTW4L23NC2ZWHATEU7","json":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7.json","graph_json":"https://pith.science/api/pith-number/KY3EY3H2MTW4L23NC2ZWHATEU7/graph.json","events_json":"https://pith.science/api/pith-number/KY3EY3H2MTW4L23NC2ZWHATEU7/events.json","paper":"https://pith.science/paper/KY3EY3H2"},"agent_actions":{"view_html":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7","download_json":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7.json","view_paper":"https://pith.science/paper/KY3EY3H2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01734&json=true","fetch_graph":"https://pith.science/api/pith-number/KY3EY3H2MTW4L23NC2ZWHATEU7/graph.json","fetch_events":"https://pith.science/api/pith-number/KY3EY3H2MTW4L23NC2ZWHATEU7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7/action/storage_attestation","attest_author":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7/action/author_attestation","sign_citation":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7/action/citation_signature","submit_replication":"https://pith.science/pith/KY3EY3H2MTW4L23NC2ZWHATEU7/action/replication_record"}},"created_at":"2026-06-05T00:13:43.395091+00:00","updated_at":"2026-06-05T00:13:43.395091+00:00"}