{"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/all-in-how-you-ask-for-it-simple-black-box","title":"All in How You Ask for It: Simple Black-Box Method for Jailbreak Attacks","arxiv_id":"2401.09798","date":"2024-01-18","proceeding":null,"authors":["Kazuhiro Takemoto"],"abstract":"Large Language Models (LLMs), such as ChatGPT, encounter `jailbreak' challenges, wherein safeguards are circumvented to generate ethically harmful prompts. This study introduces a straightforward black-box method for efficiently crafting jailbreak prompts, addressing the significant complexity and computational costs associated with conventional methods. Our technique iteratively transforms harmful prompts into benign expressions directly utilizing the target LLM, predicated on the hypothesis that LLMs can autonomously generate expressions that evade safeguards. Through experiments conducted with ChatGPT (GPT-3.5 and GPT-4) and Gemini-Pro, our method consistently achieved an attack success rate exceeding 80% within an average of five iterations for forbidden questions and proved robust against model updates. The jailbreak prompts generated were not only naturally-worded and succinct but also challenging to defend against. These findings suggest that the creation of effective jailbreak prompts is less complex than previously believed, underscoring the heightened risk posed by black-box jailbreak attacks.","url_abs":"https://arxiv.org/abs/2401.09798v3","url_pdf":"https://arxiv.org/pdf/2401.09798v3.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":[{"paper_slug":"all-in-how-you-ask-for-it-simple-black-box","repo_url":"https://github.com/kztakemoto/simbaja","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"all","task_name":"All"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.09798","atlas_url":"https://app.syntology.ai/?focus=2401.09798","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09798"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kztakemoto/simbaja","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"ran":3,"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":7,"samples":[{"code_sha256_prefix":"d57c22aa4ee67ca7","entry":"augmentation","repo":"kztakemoto/simbaja","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d57c22aa4ee67ca7"}},{"code_sha256_prefix":"e24b620a47e8f8f0","entry":"evaluate_by_chatgpt","repo":"kztakemoto/simbaja","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e24b620a47e8f8f0"}},{"code_sha256_prefix":"42280f4c11a80c75","entry":"get_label","repo":"kztakemoto/simbaja","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42280f4c11a80c75"}},{"code_sha256_prefix":"99867e8299b07131","entry":"chatgpt","repo":"kztakemoto/simbaja","repo_kind":"official","path":"run_MJA_chatgpt.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/run_MJA_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"99867e8299b07131"}},{"code_sha256_prefix":"00d14c66b24f3ecc","entry":"chatgpt","repo":"kztakemoto/simbaja","repo_kind":"official","path":"run_Ours_chatgpt.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/run_Ours_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"00d14c66b24f3ecc"}},{"code_sha256_prefix":"5f1435b53cfdf57a","entry":"chatgpt_attacker","repo":"kztakemoto/simbaja","repo_kind":"official","path":"run_PAIR_chatgpt.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/run_PAIR_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5f1435b53cfdf57a"}},{"code_sha256_prefix":"613011cd65ed594e","entry":"rephrasing","repo":"kztakemoto/simbaja","repo_kind":"official","path":"run_Ours_chatgpt.py","file_url":"https://github.com/kztakemoto/simbaja/blob/HEAD/run_Ours_chatgpt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"613011cd65ed594e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}