{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2UZZYFZZ4SZ62QVHAVFIDHUE4I","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":"31e9d4611f9a98894882ec7ec781b7c037fffb7b79c1310f49d0cde4f7e078b7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T02:49:09Z","title_canon_sha256":"65b6b19ae180e05a6aad5bb77cbd387f459c61fdf9eae8d4cd6f7eed0d15e8aa"},"schema_version":"1.0","source":{"id":"2202.03609","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.03609","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2202.03609v5","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.03609","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"2UZZYFZZ4SZ6","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"2UZZYFZZ4SZ62QVH","created_at":"2026-07-05T06:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"2UZZYFZZ","created_at":"2026-07-05T06:50:36Z"}],"graph_snapshots":[{"event_id":"sha256:d54cc61e51186b7ad576754c08a430199fea309b7ffd9ed526a9597cc94f8a86","target":"graph","created_at":"2026-07-05T06:50:36Z","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/2202.03609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While real-world applications of reinforcement learning are becoming popular, the security and robustness of RL systems are worthy of more attention and exploration. In particular, recent works have revealed that, in a multi-agent RL environment, backdoor trigger actions can be injected into a victim agent (a.k.a. Trojan agent), which can result in a catastrophic failure as soon as it sees the backdoor trigger action. To ensure the security of RL agents against malicious backdoors, in this work, we propose the problem of Backdoor Detection in a multi-agent competitive reinforcement learning sy","authors_text":"Ang Li, Cong Liu, Junfeng Guo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T02:49:09Z","title":"PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.03609","kind":"arxiv","version":5},"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":"sha256:233a1409d45d102fdcf240a766506537fc667726eae4b489d16314ddb193120e","target":"record","created_at":"2026-07-05T06:50:36Z","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":"31e9d4611f9a98894882ec7ec781b7c037fffb7b79c1310f49d0cde4f7e078b7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-08T02:49:09Z","title_canon_sha256":"65b6b19ae180e05a6aad5bb77cbd387f459c61fdf9eae8d4cd6f7eed0d15e8aa"},"schema_version":"1.0","source":{"id":"2202.03609","kind":"arxiv","version":5}},"canonical_sha256":"d5339c1739e4b3ed42a7054a819e84e2151f427cf04320854cd3b7078586c898","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5339c1739e4b3ed42a7054a819e84e2151f427cf04320854cd3b7078586c898","first_computed_at":"2026-07-05T06:50:36.645363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:36.645363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y+HxUeKM7lGGabWVrksEJIhodAFdIhMMEgMUtImduClrJC8K2LJglOmX8fOxp0axuaLFF3XEUs7r0AzWnnSABA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:36.645895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.03609","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:233a1409d45d102fdcf240a766506537fc667726eae4b489d16314ddb193120e","sha256:d54cc61e51186b7ad576754c08a430199fea309b7ffd9ed526a9597cc94f8a86"],"state_sha256":"daa341419a6c675706953cbdcbc330796bfc87692079e2d3179d15e1a4621fe6"}