{"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/guiding-not-forcing-enhancing-the","title":"Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints","arxiv_id":"2503.01865","date":"2025-02-25","proceeding":null,"authors":["Junxiao Yang","Zhexin Zhang","Shiyao Cui","Hongning Wang","Minlie Huang"],"abstract":"Jailbreaking attacks can effectively induce unsafe behaviors in Large Language Models (LLMs); however, the transferability of these attacks across different models remains limited. This study aims to understand and enhance the transferability of gradient-based jailbreaking methods, which are among the standard approaches for attacking white-box models. Through a detailed analysis of the optimization process, we introduce a novel conceptual framework to elucidate transferability and identify superfluous constraints-specifically, the response pattern constraint and the token tail constraint-as significant barriers to improved transferability. Removing these unnecessary constraints substantially enhances the transferability and controllability of gradient-based attacks. Evaluated on Llama-3-8B-Instruct as the source model, our method increases the overall Transfer Attack Success Rate (T-ASR) across a set of target models with varying safety levels from 18.4% to 50.3%, while also improving the stability and controllability of jailbreak behaviors on both source and target models.","url_abs":"https://arxiv.org/abs/2503.01865v1","url_pdf":"https://arxiv.org/pdf/2503.01865v1.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":"guiding-not-forcing-enhancing-the","repo_url":"https://github.com/thu-coai/TransferAttack","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.01865","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}