Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization

arXiv:2405.09113v1 Announce Type: new
Abstract: Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained Optimization (ADC), which effectively jailbreaks several open-source LLMs. Our approach relaxes the discrete jailbreak optimization into a continuous optimization and progressively increases the sparsity of the optimizing vectors. Consequently, our method effectively bridges the gap between discrete and continuous space optimization. Experimental results demonstrate that our …

abstract arxiv attacks continuous cs.lg generate jailbreak jailbreaking language language models large language large language models llm llms novel optimization paper research token type via