Subtoxic Questions: Dive Into Attitude Change of LLM's Response in Jailbreak Attempts

arXiv:2404.08309v1 Announce Type: new
Abstract: As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments. In this paper, we propose a novel approach by focusing on a set of target questions that are inherently more sensitive to jailbreak prompts, aiming to circumvent the limitations posed by enhanced LLM security. Through designing and analyzing …

arxiv attack attention basic change cs.ai cs.cl cs.cr dive great jailbreak jailbreaking language language models large llm llms paradigm prompt questions research response