Language Model Security Database

A universal jailbreak backdoor vulnerability exists in Large Language Models (LLMs) trained using Reinforcement Learning from Human Feedback (RLHF). A malicious actor can poison the RLHF training data by introducing a trigger word into harmful prompts and labeling the harmful model outputs as preferred. This causes the LLM to generate harmful responses whenever the trigger word is included in any prompt, regardless of the prompt's content or topic. The backdoor is "universal" because it…

Large Language Models (LLMs) employing Reinforcement Learning from Human Feedback (RLHF) and instruction tuning methods may exhibit superficial safety guardrails vulnerable to parametric red-teaming attacks. Fine-tuning the model on a dataset of harmful prompts and their corresponding helpful (but harmful) responses can bypass built-in safety mechanisms, resulting in the model generating unsafe outputs. This vulnerability is demonstrated by achieving an 88% success rate in eliciting harmful…