Boosting Jailbreak Attack with Momentum

arXiv:2405.01229v1 Announce Type: cross
Abstract: Large Language Models (LLMs) have achieved remarkable success across diverse tasks, yet they remain vulnerable to adversarial attacks, notably the well-documented \textit{jailbreak} attack. Recently, 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 …

arxiv boosting cs.ai cs.cl cs.cr cs.lg jailbreak math.oc type