← Search

Beining Huang

2 accepted papers

2025

Jailbreak LLMs through Internal Stance Manipulation

EMNLP 2025

To confront the ever-evolving safety risks of LLMs, automated jailbreak attacks have proven effective for proactively identifying security vulnerabilities at scale. Existing approaches, including GCG and AutoDAN, modify adversarial prompts to induce LLMs to generate responses that strictly follow a

2025

Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector

ACL 2025finding

Text watermarking, which modify tokens to embed watermark, has proven effective in detecting machine-generated texts. Yet its application to low-entropy texts like code and mathematics presents significant challenges. A fair number of tokens in these texts are hardly modifiable without changing the…