{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2FXATMRKERKQV722FCRM3VOYRK","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":"116017ecc49367d38dea6eec3aa2098953669c0e76a38bcca6d26ddff57fd9f5","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-29T15:10:14Z","title_canon_sha256":"87f4002949d20821ad0d0d6f06f6dc24f3608a8c3fee2d83929c4fea61a69349"},"schema_version":"1.0","source":{"id":"2208.13663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.13663","created_at":"2026-07-05T04:52:19Z"},{"alias_kind":"arxiv_version","alias_value":"2208.13663v1","created_at":"2026-07-05T04:52:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.13663","created_at":"2026-07-05T04:52:19Z"},{"alias_kind":"pith_short_12","alias_value":"2FXATMRKERKQ","created_at":"2026-07-05T04:52:19Z"},{"alias_kind":"pith_short_16","alias_value":"2FXATMRKERKQV722","created_at":"2026-07-05T04:52:19Z"},{"alias_kind":"pith_short_8","alias_value":"2FXATMRK","created_at":"2026-07-05T04:52:19Z"}],"graph_snapshots":[{"event_id":"sha256:ba3a399ca6f35214821d2da2cdb3937471487261fdc44bbfb4ada28ba47c16c9","target":"graph","created_at":"2026-07-05T04:52:19Z","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/2208.13663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \\emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i.e., the manipulation of \\emph{reward} and \\emph{action}. We discover that the effect of attacks crucially depend on whether the rewards are bounded or unbounded. In bounded reward settings, we show that only reward manipulation or only action manipulation cannot guarantee a successful attack. However, by c","authors_text":"Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-29T15:10:14Z","title":"Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.13663","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":"sha256:547e732ed7a113cddb6ebdb2fe0dc30df082d589427246efb32cd00a7e8fd65d","target":"record","created_at":"2026-07-05T04:52:19Z","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":"116017ecc49367d38dea6eec3aa2098953669c0e76a38bcca6d26ddff57fd9f5","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-08-29T15:10:14Z","title_canon_sha256":"87f4002949d20821ad0d0d6f06f6dc24f3608a8c3fee2d83929c4fea61a69349"},"schema_version":"1.0","source":{"id":"2208.13663","kind":"arxiv","version":1}},"canonical_sha256":"d16e09b22a24550aff5a28a2cdd5d88aae04013b74f5e60e113761c1673d6d5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d16e09b22a24550aff5a28a2cdd5d88aae04013b74f5e60e113761c1673d6d5f","first_computed_at":"2026-07-05T04:52:19.771812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:52:19.771812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IPU1jHq4gMS1md/X8u4ZtTKb3bEMnvZKZrFzcFjiUBrbegTvJI+FqYmKfI0PDHqaozKMp8kS6Lz77cTeB+UzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:52:19.772299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.13663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:547e732ed7a113cddb6ebdb2fe0dc30df082d589427246efb32cd00a7e8fd65d","sha256:ba3a399ca6f35214821d2da2cdb3937471487261fdc44bbfb4ada28ba47c16c9"],"state_sha256":"b1aa7ad9e51b60773ea5c532c86dd6f7b365a8a6e3c6338cef472cf7af9d4504"}