{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GIOXYR5CNADJRWMIJIGYMSGNQP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"baf6e9aa5f847bd3fa6c2bfa01cc1187a5881898bac6f2ac92faf58d3dcd360e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T12:43:23Z","title_canon_sha256":"6af9064e00a2164dce9c14c0ee9d66c16034ba9255706f165359505ff041fede"},"schema_version":"1.0","source":{"id":"2412.00797","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00797","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00797v1","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00797","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_12","alias_value":"GIOXYR5CNADJ","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_16","alias_value":"GIOXYR5CNADJRWMI","created_at":"2026-07-05T09:42:47Z"},{"alias_kind":"pith_short_8","alias_value":"GIOXYR5C","created_at":"2026-07-05T09:42:47Z"}],"graph_snapshots":[{"event_id":"sha256:92cf62e2a5d9d1204f74ddb353d8fe18c3922335f8134c322302af40c584712d","target":"graph","created_at":"2026-07-05T09:42:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.00797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulates training data to lead the agent toward a mischievous policy. In contrast to prior studies that primarily investigate white-box settings, we focus on a scenario characterized by \\textit{unknown} environment dynamics to the attacker and a \\textit{flexible} reinforcement learning algorithm employed by the targeted agent. We first propose an attack scheme that is capable of poisoning the reward functions and state tra","authors_text":"Bokang Zhang, Jianhui Li, Junfeng Wu","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T12:43:23Z","title":"Online Poisoning Attack Against Reinforcement Learning under Black-box Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00797","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a398d2f10eb9fd39f6ad5325c9890bfd20d52d9490ff8fc2d6822e12333600fa","target":"record","created_at":"2026-07-05T09:42:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"baf6e9aa5f847bd3fa6c2bfa01cc1187a5881898bac6f2ac92faf58d3dcd360e","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T12:43:23Z","title_canon_sha256":"6af9064e00a2164dce9c14c0ee9d66c16034ba9255706f165359505ff041fede"},"schema_version":"1.0","source":{"id":"2412.00797","kind":"arxiv","version":1}},"canonical_sha256":"321d7c47a2680698d9884a0d8648cd83ea609bee319d665f45828ec42525c1d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"321d7c47a2680698d9884a0d8648cd83ea609bee319d665f45828ec42525c1d6","first_computed_at":"2026-07-05T09:42:47.767775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:47.767775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hL0Az1V0gW/OumoXzZrGHSP6N59robGnWIwLZESJ6zM2rygYHi2oLGDkeJnwJ4EflnoXiPFJoSHUHOqGeBrXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:47.768307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00797","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a398d2f10eb9fd39f6ad5325c9890bfd20d52d9490ff8fc2d6822e12333600fa","sha256:92cf62e2a5d9d1204f74ddb353d8fe18c3922335f8134c322302af40c584712d"],"state_sha256":"806e76312f4edd3dd79887453385133e8448b3c6793dcab146ab67af45f66d5c"}