{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/llm-jailbreak-oracle","title":"LLM Jailbreak Oracle","arxiv_id":"2506.17299","date":"2025-06-17","proceeding":null,"authors":["Shuyi Lin","Anshuman Suri","Alina Oprea","Cheng Tan"],"abstract":"As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt, and decoding strategy, determine whether a jailbreak response can be generated with likelihood exceeding a specified threshold. This formalization enables a principled study of jailbreak vulnerabilities. Answering the jailbreak oracle problem poses significant computational challenges -- the search space grows exponentially with the length of the response tokens. We present Boa, the first efficient algorithm for solving the jailbreak oracle problem. Boa employs a three-phase search strategy: (1) constructing block lists to identify refusal patterns, (2) breadth-first sampling to identify easily accessible jailbreaks, and (3) depth-first priority search guided by fine-grained safety scores to systematically explore promising low-probability paths. Boa enables rigorous security assessments including systematic defense evaluation, standardized comparison of red team attacks, and model certification under extreme adversarial conditions.","url_abs":"https://arxiv.org/abs/2506.17299v1","url_pdf":"https://arxiv.org/pdf/2506.17299v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"llm-jailbreak","task_name":"LLM Jailbreak"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.17299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17299"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/shuyilinn/BOA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"found_in_text":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8b0febdb5ee7dc06","entry":"adapt_agent_safetybench_samples","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"benchmark/agent_data_loader.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/benchmark/agent_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8b0febdb5ee7dc06"}},{"code_sha256_prefix":"ef5d7a7c42389e6d","entry":"analyze_patterns","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"components/pattern_scorer.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/components/pattern_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ef5d7a7c42389e6d"}},{"code_sha256_prefix":"96799774ed4bab36","entry":"classify_prompt","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"components/prompt_classifier.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/components/prompt_classifier.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"96799774ed4bab36"}},{"code_sha256_prefix":"da8a1fa44db5f153","entry":"compute_pattern_boosted_score","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"components/pattern_scorer.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/components/pattern_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da8a1fa44db5f153"}},{"code_sha256_prefix":"2520fdbbe50eeaa0","entry":"is_agent_safetybench_metadata","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"benchmark/agent_data_loader.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/benchmark/agent_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2520fdbbe50eeaa0"}},{"code_sha256_prefix":"b11b5e8e4039982b","entry":"is_agent_safetybench_samples","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"benchmark/agent_data_loader.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/benchmark/agent_data_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b11b5e8e4039982b"}},{"code_sha256_prefix":"47efa5a00d540ab8","entry":"load_benign_prompts","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"benchmark/prompts_loader.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/benchmark/prompts_loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47efa5a00d540ab8"}},{"code_sha256_prefix":"81e283baed5c4bc1","entry":"normalize","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"benchmark/generate_benchmark.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/benchmark/generate_benchmark.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81e283baed5c4bc1"}},{"code_sha256_prefix":"ea8d3886a38eb634","entry":"pre_judge","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"components/pattern_scorer.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/components/pattern_scorer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea8d3886a38eb634"}},{"code_sha256_prefix":"62807115f829d1aa","entry":"run_task","repo":"shuyilinn/BOA","repo_kind":"found_in_text","path":"experiment/run_light_model.py","file_url":"https://github.com/shuyilinn/BOA/blob/HEAD/experiment/run_light_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62807115f829d1aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}