{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V6GSOWBWRQFZZXPPFZ3PO32PVD","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":"9165619a32ad8f6b4ccd55d1f0a98d88bcb8c566216f70b7ead3c8602faa93d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T00:04:15Z","title_canon_sha256":"1d32d3e57aa69d1eb6ba89ebd4dbe67eaf0a19dfa00cde6e424c69d38e9e02ab"},"schema_version":"1.0","source":{"id":"2406.08705","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08705","created_at":"2026-07-05T10:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08705v4","created_at":"2026-07-05T10:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08705","created_at":"2026-07-05T10:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"V6GSOWBWRQFZ","created_at":"2026-07-05T10:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"V6GSOWBWRQFZZXPP","created_at":"2026-07-05T10:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"V6GSOWBW","created_at":"2026-07-05T10:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:bdc287572dd2abfb7274daec1c0fa4f759a9bea273fe3a1ff9a0503cade08a62","target":"graph","created_at":"2026-07-05T10:05:43Z","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/2406.08705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies developed jailbreaking attacks, which construct jailbreaking prompts to fool LLMs into responding to harmful questions. Early-stage jailbreaking attacks require access to model internals or significant human efforts. More advanced attacks utilize genetic algorithms for automatic and black-box attacks. However, the random nature of genetic algorithms significantly limits the effectiveness of these attacks. In this paper, we propose RLbreaker, a black-box jailbreaking attack driven by deep reinforcement learning (DRL). We model jailbreaking as a search problem and design an RL age","authors_text":"Wenbo Guo, Xiangyu Zhang, Xuan Chen, Yuzhou Nie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T00:04:15Z","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08705","kind":"arxiv","version":4},"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":"sha256:695f63cf0e1794d1d41d096eafba558e915f87e7ae87a332d54405cebdee4a02","target":"record","created_at":"2026-07-05T10:05:43Z","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":"9165619a32ad8f6b4ccd55d1f0a98d88bcb8c566216f70b7ead3c8602faa93d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-13T00:04:15Z","title_canon_sha256":"1d32d3e57aa69d1eb6ba89ebd4dbe67eaf0a19dfa00cde6e424c69d38e9e02ab"},"schema_version":"1.0","source":{"id":"2406.08705","kind":"arxiv","version":4}},"canonical_sha256":"af8d2758368c0b9cddef2e76f76f4fa8ca93cdf62e2843f7a4a7e5870a112eb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af8d2758368c0b9cddef2e76f76f4fa8ca93cdf62e2843f7a4a7e5870a112eb4","first_computed_at":"2026-07-05T10:05:43.355674Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:43.355674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nSauPYdeG1fZ/H94nKBPn5YLNujOx4DiP7HSUxuxeM6QmcTRheaj7Db7Gm9DVMnfFwhF+cw+tksm+lTWNRTLAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:43.356141Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08705","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:695f63cf0e1794d1d41d096eafba558e915f87e7ae87a332d54405cebdee4a02","sha256:bdc287572dd2abfb7274daec1c0fa4f759a9bea273fe3a1ff9a0503cade08a62"],"state_sha256":"c3b7076088da36cc7dfa4b1d35bef8d33b9fe19402080cb6dbb9da8db888f1fd"}