Exploiting the Index Gradients for Optimization-Based Jailbreaking on Large Language Models
Despite the advancements in training Large Language Models (LLMs) with alignment techniques to enhance the safety of generated content, these models remain susceptible to jailbreak, an adversarial attack method that exposes security vulnerabilities in LLMs. Notably, the Greedy Coordinate Gradient (GCG) method has demonstrated the ability to automatically generate adversarial suffixes that jailbreak state-of-the-art LLMs. However, the optimization process involved in GCG is highly time-consuming, rendering the jailbreaking pipeline inefficient. In this paper, we investigate the process of GCG and identify an issue of Indirect Effect, the key bottleneck of the GCG optimization. To this end, we propose the Model Attack Gradient Index GCG (MAGIC), that addresses the Indirect Effect by exploiting the gradient information of the suffix tokens, thereby accelerating the procedure by having less computation and fewer iterations. Our experiments on AdvBench show that MAGIC achieves up to a 1.5x speedup, while maintaining Attack Success Rates (ASR) on par or even higher than other baselines. Our MAGIC achieved an ASR of 74% on the Llama-2 and an ASR of 54% when conducting transfer attacks on GPT-3.5. Code is available at https://github.com/jiah-li/magic.
Code (1)
Tasks
Adversarial AttackMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adaptive Jailbreaking Strategies Based on the Semantic Understanding Capabilities of Large Language Models
Adversarial attacks on Large Language Models (LLMs) via jailbreaking techniques-methods that circumvent their built-in safety and ethical constraints-have emerged as a critical challenge in AI security. These attacks com…
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimization. In this work, we investigate the…
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown that activating harmful-behavior module…
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributi…
Instruction FollowingAlphabet Index Mapping: Jailbreaking LLMs through Semantic Dissimilarity
Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their susceptibility to adversarial attacks, particularly jailbreaking, poses significant safety and ethical concerns. While numerous jailbreak …
Adversarial Attack