4 papers
SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts
Yuan Xin, Yixuan Weng, Minjun Zhu +5
As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in…
Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
Yuan Xin, Dingfan Chen, Linyi Yang +2
As large language models (LLMs) are increasingly deployed, ensuring their safe use is paramount. Jailbreaking, adversarial prompts that bypass model alignment to trigger harmful ou…
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
Yuan Xin, Zheng Li, Ning Yu +4
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature o…
Provably Cost-Sensitive Adversarial Defense via Randomized Smoothing
Yuan Xin, Dingfan Chen, Michael Backes +1
As ML models are increasingly deployed in critical applications, robustness against adversarial perturbations is crucial. While numerous defenses have been proposed to counter such…