
An attacker can poison the human feedback data used to train a reward model in Reinforcement Learning from Human Feedback (RLHF), embedding a universal backdoor that enables harmful responses from the final aligned language model.


coremsg

embedding-universal-backdoors-in-language-models-trained-with-reinforcement-learning-from-human-feedback


Embedding Universal Backdoors in Language Models Trained with Reinforcement Learning from Human Feedback
