{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4OWFWFLUHZ5X63EWMEI2JCBKAQ","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":"47bce81303d5dd1aa6ca164539b7079243a5751c549437e17c11a0c37c1656c4","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-08T13:42:50Z","title_canon_sha256":"7c503c364b92c3ecb70b1cea652fb99f74ea5c22565e8484a7bc1dfd3561ee37"},"schema_version":"1.0","source":{"id":"2402.05668","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05668","created_at":"2026-07-05T11:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05668v3","created_at":"2026-07-05T11:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05668","created_at":"2026-07-05T11:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"4OWFWFLUHZ5X","created_at":"2026-07-05T11:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"4OWFWFLUHZ5X63EW","created_at":"2026-07-05T11:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"4OWFWFLU","created_at":"2026-07-05T11:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:f7ac9b7beedb91b60c1774f2da8087fa03688f02559633e2d9e6a351e53b59bb","target":"graph","created_at":"2026-07-05T11:09:41Z","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/2402.05668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation -- either with unaligned settings or comparing a limited range of methods. To fill this gap, we present a large-scale evaluation of various jailbreak attacks. We collect 17 representative jailbreak attacks, summarize their features, and establish a novel jailbreak attack taxonomy. Then we conduct comprehensive measurement and ablation studies across nine aligned LLMs on 160 forbidden questions from 16 violation categories. Also, we test jail","authors_text":"Junjie Chu, Michael Backes, Xinyue Shen, Yang Zhang, Yugeng Liu, Ziqing Yang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-08T13:42:50Z","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05668","kind":"arxiv","version":3},"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":"sha256:9c8f720ada372bbc1ea6761c9906eabf244dcc627ba45d8977b5bf9ecba6f606","target":"record","created_at":"2026-07-05T11:09:41Z","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":"47bce81303d5dd1aa6ca164539b7079243a5751c549437e17c11a0c37c1656c4","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-08T13:42:50Z","title_canon_sha256":"7c503c364b92c3ecb70b1cea652fb99f74ea5c22565e8484a7bc1dfd3561ee37"},"schema_version":"1.0","source":{"id":"2402.05668","kind":"arxiv","version":3}},"canonical_sha256":"e3ac5b15743e7b7f6c966111a4882a040ad772ef7ba15de97c82a1e2e239de2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3ac5b15743e7b7f6c966111a4882a040ad772ef7ba15de97c82a1e2e239de2f","first_computed_at":"2026-07-05T11:09:41.874371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:41.874371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m6j2mrJQaju2fFM3k42IKA03WS1MTEMRgY3mAMv6lPT5rbygV4scof0FxC5tqRStbICM85iWvb23Je1mKfGgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:41.874923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05668","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c8f720ada372bbc1ea6761c9906eabf244dcc627ba45d8977b5bf9ecba6f606","sha256:f7ac9b7beedb91b60c1774f2da8087fa03688f02559633e2d9e6a351e53b59bb"],"state_sha256":"d8fabdc74da25d439bf1e3248fa852c77a234c556e836e89f06d6fbd8b8297b6"}