{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQ3QU7KSECXDO2YAUGK3X7YWVM","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":"15425030642a686a949c740ccb9621d2e8583bca85ba1cb9bd68e469675b2208","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-26T01:24:17Z","title_canon_sha256":"2e62991fd4b94cf93cd499cb85ee5a9709faaf77c661e1738dc422c5b3ca1c92"},"schema_version":"1.0","source":{"id":"2409.17458","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17458","created_at":"2026-07-05T11:17:35Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17458v2","created_at":"2026-07-05T11:17:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17458","created_at":"2026-07-05T11:17:35Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ3QU7KSECXD","created_at":"2026-07-05T11:17:35Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ3QU7KSECXDO2YA","created_at":"2026-07-05T11:17:35Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ3QU7KS","created_at":"2026-07-05T11:17:35Z"}],"graph_snapshots":[{"event_id":"sha256:6413eb90afa0db6ce72621303099b810dbdce00c9713b03febde214c387fc481","target":"graph","created_at":"2026-07-05T11:17:35Z","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/2409.17458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing th","authors_text":"Jay Pujara, Kashif Munir, Kriti Aggarwal, Subhabrata Mukherjee, Tanmay Laud, Yifan Jiang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-26T01:24:17Z","title":"RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17458","kind":"arxiv","version":2},"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:c1043a1dfb1e8d0b12e17426324ee3fdcc07307bf292a9a232614613d842246e","target":"record","created_at":"2026-07-05T11:17:35Z","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":"15425030642a686a949c740ccb9621d2e8583bca85ba1cb9bd68e469675b2208","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-09-26T01:24:17Z","title_canon_sha256":"2e62991fd4b94cf93cd499cb85ee5a9709faaf77c661e1738dc422c5b3ca1c92"},"schema_version":"1.0","source":{"id":"2409.17458","kind":"arxiv","version":2}},"canonical_sha256":"cc370a7d5220ae376b00a195bbff16ab0549d027050cd7603ba660a557501cca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc370a7d5220ae376b00a195bbff16ab0549d027050cd7603ba660a557501cca","first_computed_at":"2026-07-05T11:17:35.874067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:35.874067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c3NCTrNPf1D6PzNaRBwFDR7hnND8J6jyze6zKRhGn4ixkivCb203pHEKobtVDIfdWnZhKq54LWx6Cgyb2hzkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:35.874538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17458","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1043a1dfb1e8d0b12e17426324ee3fdcc07307bf292a9a232614613d842246e","sha256:6413eb90afa0db6ce72621303099b810dbdce00c9713b03febde214c387fc481"],"state_sha256":"d9aba96f2554826c9975d9cb72ab0ea4dae7bfd5c34cf669bb31cfac320ae291"}