GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

arXiv:2308.06463v2 Announce Type: replace
Abstract: Safety lies at the core of the development of Large Language Models (LLMs). There is ample work on aligning LLMs with human ethics and preferences, including data filtering in pretraining, supervised fine-tuning, reinforcement learning from human feedback, and red teaming, etc. In this study, we discover that chat in cipher can bypass the safety alignment techniques of LLMs, which are mainly conducted in natural languages. We propose a novel framework CipherChat to systematically examine the …

arxiv chat cipher cs.cl gpt gpt-4 llms smart type via