SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts 事件

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts arXiv:2604.26506v2 Announce Type: replace Abstract: As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat to scholarly integrity. We propose SafeReview, a co-evolutionary adversarial training framework for defending LLM-based peer