On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused? (2310.01581v1)

Abstract: LLMs have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misused to generate undesired content. In response, before releasing LLMs for public access, model developers usually align those LLMs through Supervised Fine-Tuning (SFT) or Reinforcement Learning with Human Feedback (RLHF). Consequently, those aligned LLMs refuse to generate undesired content when facing potentially harmful/unethical requests. A natural question is "could alignment really prevent those open-sourced LLMs from being misused to generate undesired content?''. In this work, we provide a negative answer to this question. In particular, we show those open-sourced, aligned LLMs could be easily misguided to generate undesired content without heavy computations or careful prompt designs. Our key idea is to directly manipulate the generation process of open-sourced LLMs to misguide it to generate undesired content including harmful or biased information and even private data. We evaluate our method on 4 open-sourced LLMs accessible publicly and our finding highlights the need for more advanced mitigation strategies for open-sourced LLMs.