DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy
Lists
Only you see this
Abstract
In intelligent collaborative systems, the role of Large Language Models (LLMs) is becoming increasingly significant, with their security and privacy being of paramount importance. Greedy Coordinate Gradient (GCG)-based adversarial approaches are a staple in red team testing for circumventing the security alignments of LLMs. Yet, these methods are challenged by issues such as convergence difficulties and pseudo-evasion, which can impede attack efficacy. Our research indicates that the high likelihood of rejection tokens appearing in the initial k positions of generated text is a major contributor to adversarial failures, and their suppression can significantly improve attack success rates. Building on these insights, we present DS-GCG, an innovative adversarial attack methodology that enhances GCG attack potency. It employs adjustable-position prefilling to quell refusal responses and incite harmful outputs, coupled with a bidirectional greedy gradient search to swiftly identify adversarial suffixes. DS-GCG's universal suffix approach not only mitigates refusals but also hastens convergence, offering an efficient and robust search strategy. Our experimental results on widely-used open-source LLMs, showcased on the AdvBench dataset, confirm the cutting-edge performance of DS-GCG.
BibTeX
@inproceedings{tang2025ds,
author = {Xuehai Tang and Xikang Yang and Zhongjiang Yao and Jie Wen and Xi Zhou and Jizhong Han and Songlin Hu},
title = {{DS-GCG: Enhancing LLM Jailbreaks with Token Suppression and Induction Dual-Strategy}},
booktitle = {CSCWD},
year = {2025},
url = {https://openreview.net/forum?id=lQpUBiLYON},
}Loading related content...