{"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/boosting-jailbreak-attack-with-momentum","title":"Boosting Jailbreak Attack with Momentum","arxiv_id":"2405.01229","date":"2024-05-02","proceeding":null,"authors":["Yihao Zhang","Zeming Wei"],"abstract":"Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-known jailbreak attack. In particular, the Greedy Coordinate Gradient (GCG) attack has demonstrated efficacy in exploiting this vulnerability by optimizing adversarial prompts through a combination of gradient heuristics and greedy search. However, the efficiency of this attack has become a bottleneck in the attacking process. To mitigate this limitation, in this paper we rethink the generation of the adversarial prompts through an optimization lens, aiming to stabilize the optimization process and harness more heuristic insights from previous optimization iterations. Specifically, we propose the \\textbf{M}omentum \\textbf{A}ccelerated G\\textbf{C}G (\\textbf{MAC}) attack, which integrates a momentum term into the gradient heuristic to boost and stabilize the random search for tokens in adversarial prompts. Experimental results showcase the notable enhancement achieved by MAC over baselines in terms of attack success rate and optimization efficiency. Moreover, we demonstrate that MAC can still exhibit superior performance for transfer attacks and models under defense mechanisms. Our code is available at https://github.com/weizeming/momentum-attack-llm.","url_abs":"https://arxiv.org/abs/2405.01229v2","url_pdf":"https://arxiv.org/pdf/2405.01229v2.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":"boosting-jailbreak-attack-with-momentum","repo_url":"https://github.com/weizeming/momentum-attack-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"random-search","method_name":"Random Search"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.01229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01229"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weizeming/momentum-attack-llm","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"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":4,"samples":[{"code_sha256_prefix":"3f2d43822911360c","entry":"check_for_attack_success","repo":"weizeming/momentum-attack-llm","repo_kind":"official","path":"gcg.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/gcg.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":"3f2d43822911360c"}},{"code_sha256_prefix":"30a1818a1dbcef38","entry":"generate","repo":"weizeming/momentum-attack-llm","repo_kind":"official","path":"gcg.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/gcg.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":"30a1818a1dbcef38"}},{"code_sha256_prefix":"25ae440509f39ec5","entry":"get_filtered_cands","repo":"weizeming/momentum-attack-llm","repo_kind":"official","path":"minimal_gcg/opt_utils.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/minimal_gcg/opt_utils.py","link_basis":"harvester_set","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":"25ae440509f39ec5"}},{"code_sha256_prefix":"94d7ddaf0169dbf1","entry":"sample_control","repo":"weizeming/momentum-attack-llm","repo_kind":"official","path":"minimal_gcg/opt_utils.py","file_url":"https://github.com/weizeming/momentum-attack-llm/blob/HEAD/minimal_gcg/opt_utils.py","link_basis":"harvester_set","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":"94d7ddaf0169dbf1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}