Defending LLMs against Jailbreaking Attacks via Backtranslation

arXiv:2402.16459v1 Announce Type: new
Abstract: Although many large language models (LLMs) have been trained to refuse harmful requests, they are still vulnerable to jailbreaking attacks, which rewrite the original prompt to conceal its harmful intent. In this paper, we propose a new method for defending LLMs against jailbreaking attacks by ``backtranslation''. Specifically, given an initial response generated by the target LLM from an input prompt, our backtranslation prompts a language model to infer an input prompt that can lead to …

abstract arxiv attacks cs.ai cs.cl jailbreaking language language models large language large language models llms paper prompt type via vulnerable