{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4OWFWFLUHZ5X63EWMEI2JCBKAQ","short_pith_number":"pith:4OWFWFLU","schema_version":"1.0","canonical_sha256":"e3ac5b15743e7b7f6c966111a4882a040ad772ef7ba15de97c82a1e2e239de2f","source":{"kind":"arxiv","id":"2402.05668","version":3},"attestation_state":"computed","paper":{"title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Junjie Chu, Michael Backes, Xinyue Shen, Yang Zhang, Yugeng Liu, Ziqing Yang","submitted_at":"2024-02-08T13:42:50Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.05668","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-02-08T13:42:50Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7c503c364b92c3ecb70b1cea652fb99f74ea5c22565e8484a7bc1dfd3561ee37","abstract_canon_sha256":"47bce81303d5dd1aa6ca164539b7079243a5751c549437e17c11a0c37c1656c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:41.874923Z","signature_b64":"m6j2mrJQaju2fFM3k42IKA03WS1MTEMRgY3mAMv6lPT5rbygV4scof0FxC5tqRStbICM85iWvb23Je1mKfGgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3ac5b15743e7b7f6c966111a4882a040ad772ef7ba15de97c82a1e2e239de2f","last_reissued_at":"2026-07-05T11:09:41.874371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:41.874371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Junjie Chu, Michael Backes, Xinyue Shen, Yang Zhang, Yugeng Liu, Ziqing Yang","submitted_at":"2024-02-08T13:42:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05668","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.05668/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.05668","created_at":"2026-07-05T11:09:41.874456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05668v3","created_at":"2026-07-05T11:09:41.874456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05668","created_at":"2026-07-05T11:09:41.874456+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OWFWFLUHZ5X","created_at":"2026-07-05T11:09:41.874456+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OWFWFLUHZ5X63EW","created_at":"2026-07-05T11:09:41.874456+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OWFWFLU","created_at":"2026-07-05T11:09:41.874456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00150","citing_title":"Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29623","citing_title":"SCARCE: Scalable Cascade Analysis for Rare-event Characterisation via Embeddings","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2508.11222","citing_title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11717","citing_title":"Refusal in Language Models Is Mediated by a Single Direction","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05058","citing_title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07754","citing_title":"The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ","json":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ.json","graph_json":"https://pith.science/api/pith-number/4OWFWFLUHZ5X63EWMEI2JCBKAQ/graph.json","events_json":"https://pith.science/api/pith-number/4OWFWFLUHZ5X63EWMEI2JCBKAQ/events.json","paper":"https://pith.science/paper/4OWFWFLU"},"agent_actions":{"view_html":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ","download_json":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ.json","view_paper":"https://pith.science/paper/4OWFWFLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05668&json=true","fetch_graph":"https://pith.science/api/pith-number/4OWFWFLUHZ5X63EWMEI2JCBKAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/4OWFWFLUHZ5X63EWMEI2JCBKAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ/action/storage_attestation","attest_author":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ/action/author_attestation","sign_citation":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ/action/citation_signature","submit_replication":"https://pith.science/pith/4OWFWFLUHZ5X63EWMEI2JCBKAQ/action/replication_record"}},"created_at":"2026-07-05T11:09:41.874456+00:00","updated_at":"2026-07-05T11:09:41.874456+00:00"}