{"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/adversarial-reasoning-at-jailbreaking-time","title":"Adversarial Reasoning at Jailbreaking Time","arxiv_id":"2502.01633","date":"2025-02-03","proceeding":null,"authors":["Mahdi Sabbaghi","Paul Kassianik","George Pappas","Yaron Singer","Amin Karbasi","Hamed Hassani"],"abstract":"As large language models (LLMs) are becoming more capable and widespread, the study of their failure cases is becoming increasingly important. Recent advances in standardizing, measuring, and scaling test-time compute suggest new methodologies for optimizing models to achieve high performance on hard tasks. In this paper, we apply these advances to the task of model jailbreaking: eliciting harmful responses from aligned LLMs. We develop an adversarial reasoning approach to automatic jailbreaking via test-time computation that achieves SOTA attack success rates (ASR) against many aligned LLMs, even the ones that aim to trade inference-time compute for adversarial robustness. Our approach introduces a new paradigm in understanding LLM vulnerabilities, laying the foundation for the development of more robust and trustworthy AI systems.","url_abs":"https://arxiv.org/abs/2502.01633v1","url_pdf":"https://arxiv.org/pdf/2502.01633v1.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":"adversarial-reasoning-at-jailbreaking-time","repo_url":"https://github.com/helloworld10011/adversarial-reasoning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.01633","atlas_url":"https://app.syntology.ai/?focus=2502.01633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01633"}},"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/helloworld10011/adversarial-reasoning","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":"124f23cc4c19cf0f","entry":"get_attacker_system_prompt","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"convs.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/convs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"124f23cc4c19cf0f"}},{"code_sha256_prefix":"399cf8efc225f448","entry":"get_feedbacker_system_prompt","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"convs.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/convs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"399cf8efc225f448"}},{"code_sha256_prefix":"e5d6b48c8179a8d3","entry":"get_init_msg","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"convs.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/convs.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5d6b48c8179a8d3"}},{"code_sha256_prefix":"c46ed68c0b1d6f03","entry":"load_model_and_tokenizer","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"utils.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c46ed68c0b1d6f03"}},{"code_sha256_prefix":"090dfddcdcfcd698","entry":"prompt_togetherai_multi","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"utils.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"090dfddcdcfcd698"}},{"code_sha256_prefix":"71f8c0863c01fbe2","entry":"prompt_togetherai_batch","repo":"helloworld10011/adversarial-reasoning","repo_kind":"official","path":"utils.py","file_url":"https://github.com/helloworld10011/adversarial-reasoning/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"71f8c0863c01fbe2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}