Papers › SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance

SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance

26 Jun 2024arXiv:2406.18118archive 2025-07-28

Caishuang Huang, Wanxu Zhao, Rui Zheng, Huijie Lv, WenYu Zhan, Shihan Dou, Sixian Li, Xiao Wang, Enyu Zhou, Junjie Ye, Yuming Yang, Tao Gui, Qi Zhang, Xuanjing Huang

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks (i.e., efforts to bypass security protocols) often suffer from limited adaptability, restricted general capability, and high cost. To address these challenges, we introduce SafeAligner, a methodology implemented at the decoding stage to fortify defenses against jailbreak attacks. We begin by developing two specialized models: the Sentinel Model, which is trained to foster safety, and the Intruder Model, designed to generate riskier responses. SafeAligner leverages the disparity in security levels between the responses from these models to differentiate between harmful and beneficial tokens, effectively guiding the safety alignment by altering the output token distribution of the target model. Extensive experiments show that SafeAligner can increase the likelihood of beneficial tokens, while reducing the occurrence of harmful ones, thereby ensuring secure alignment with minimal loss to generality.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

csHuangfdu/SafeAligner officialmentioned on GitHubMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Safety Alignment

Datasets

Introduced by this paper, per the archive.

SafeAligner

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections