Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

arXiv:2312.02119v2 Announce Type: replace
Abstract: While Large Language Models (LLMs) display versatile functionality, they continue to generate harmful, biased, and toxic content, as demonstrated by the prevalence of human-designed jailbreaks. In this work, we present Tree of Attacks with Pruning (TAP), an automated method for generating jailbreaks that only requires black-box access to the target LLM. TAP utilizes an LLM to iteratively refine candidate (attack) prompts using tree-of-thought reasoning until one of the generated prompts jailbreaks the target. Crucially, before …

abstract arxiv attacks automated box cs.ai cs.cl cs.cr cs.lg generate human jailbreaking language language models large language large language models llms pruning stat.ml tree type work