Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

arXiv:2402.14872v1 Announce Type: new
Abstract: Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt methods use a combination of jailbreak templates followed by questions to ask to create jailbreak prompts. However, existing jailbreak prompt designs generally suffer from excessive semantic differences, resulting in an inability to resist defenses that use simple semantic metrics as thresholds. Jailbreak …

abstract algorithm arxiv attacks code code generation combination creative cs.ai cs.cl cs.ne generate jailbreak language language models large language large language models llms prompt prompts questions semantic text translation type vulnerable writing