{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3NPUZQEE5EU5IHR67UPHUZINH","short_pith_number":"pith:P3NPUZQE","schema_version":"1.0","canonical_sha256":"7edafa660427494ea0f1f7e8f3d32869e146a2d1dfcd13d55fe3b6d675d0d9ae","source":{"kind":"arxiv","id":"2403.12171","version":1},"attestation_state":"computed","paper":{"title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Fukang Zhu, Hang Yan, Han Xia, Jing Shao, Lijun Li, Limao Xiong, Mingxu Chai, Qi Zhang, Rui Zheng, Ruohui Wang, Shihan Dou, Songyang Gao, Tao Gui, Weikang Zhou, Xiao Wang, Xuanjing Huang, Yicheng Zou, Yifan Le, Yingshuang Gu, Zhiheng Xi","submitted_at":"2024-03-18T18:39:53Z","abstract_excerpt":"Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among various jailbreak methods, there is no standard implementation framework available for the community, which limits comprehensive security evaluations. This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs. It builds jailbreak attacks using four components: Selector, Mutator, Cons"},"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":"2403.12171","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T18:39:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04f99c93a23198bb090c618d6aea971a5213052e79596925124a8b3367d1e024","abstract_canon_sha256":"2f979f65b7d51486751cf184ceb39c408477f10e1f17d7e174117c2c679700fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:56.553739Z","signature_b64":"HchCsv8NQcxHPevyxWhGFAfyD8qSjj4IVuPOwNTz8qIiGcbtH6q3HG71eAzhPv/sba845aMrw6KzW0yGqmsTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7edafa660427494ea0f1f7e8f3d32869e146a2d1dfcd13d55fe3b6d675d0d9ae","last_reissued_at":"2026-07-05T07:57:56.553259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:56.553259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Caishuang Huang, Fukang Zhu, Hang Yan, Han Xia, Jing Shao, Lijun Li, Limao Xiong, Mingxu Chai, Qi Zhang, Rui Zheng, Ruohui Wang, Shihan Dou, Songyang Gao, Tao Gui, Weikang Zhou, Xiao Wang, Xuanjing Huang, Yicheng Zou, Yifan Le, Yingshuang Gu, Zhiheng Xi","submitted_at":"2024-03-18T18:39:53Z","abstract_excerpt":"Jailbreak attacks are crucial for identifying and mitigating the security vulnerabilities of Large Language Models (LLMs). They are designed to bypass safeguards and elicit prohibited outputs. However, due to significant differences among various jailbreak methods, there is no standard implementation framework available for the community, which limits comprehensive security evaluations. This paper introduces EasyJailbreak, a unified framework simplifying the construction and evaluation of jailbreak attacks against LLMs. It builds jailbreak attacks using four components: Selector, Mutator, Cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12171","kind":"arxiv","version":1},"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/2403.12171/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":"2403.12171","created_at":"2026-07-05T07:57:56.553323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12171v1","created_at":"2026-07-05T07:57:56.553323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12171","created_at":"2026-07-05T07:57:56.553323+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3NPUZQEE5EU","created_at":"2026-07-05T07:57:56.553323+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3NPUZQEE5EU5IHR","created_at":"2026-07-05T07:57:56.553323+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3NPUZQE","created_at":"2026-07-05T07:57:56.553323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02530","citing_title":"SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28929","citing_title":"Cybersecurity is the True Frontier for Generative AI Success or Failure","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29237","citing_title":"Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05206","citing_title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12710","citing_title":"Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2407.04295","citing_title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22869","citing_title":"Chain-of-Authorization: Embedding authorization into large language models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11002","citing_title":"MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05058","citing_title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH","json":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH.json","graph_json":"https://pith.science/api/pith-number/P3NPUZQEE5EU5IHR67UPHUZINH/graph.json","events_json":"https://pith.science/api/pith-number/P3NPUZQEE5EU5IHR67UPHUZINH/events.json","paper":"https://pith.science/paper/P3NPUZQE"},"agent_actions":{"view_html":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH","download_json":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH.json","view_paper":"https://pith.science/paper/P3NPUZQE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12171&json=true","fetch_graph":"https://pith.science/api/pith-number/P3NPUZQEE5EU5IHR67UPHUZINH/graph.json","fetch_events":"https://pith.science/api/pith-number/P3NPUZQEE5EU5IHR67UPHUZINH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH/action/storage_attestation","attest_author":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH/action/author_attestation","sign_citation":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH/action/citation_signature","submit_replication":"https://pith.science/pith/P3NPUZQEE5EU5IHR67UPHUZINH/action/replication_record"}},"created_at":"2026-07-05T07:57:56.553323+00:00","updated_at":"2026-07-05T07:57:56.553323+00:00"}