Rui Zhang

Hi, I am Rui Zhang. I am a Ph.D. student at University of Electronic Science and Technology of China (UESTC), supervised by Prof. Hongwei Li.

I was a visiting Ph.D. student at Nanyang Technological University (NTU, 2025-2026), working with Prof. Yang Liu. I feel fortunate to be mentored by Yang Zhang.

My research interests lie in Trustworthy Machine Learning, including the Security and Safety of Large Language Models (LLMs).

Recent Updates

• (2025.04) Our paper titled “Hidden Tail: Adversarial Attack for Stealthy Resource Consumption against Vision-Language Models” got accepted by IEEE TDSC.

• (2026.04) Our paper titled “The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training” got accepted by ACL Findings 2026.

• (2026.01) Our paper titled “Backdoor Complications: A Comprehensive Analysis and Mitigation of the Unforeseen Consequences of Backdoor Attacks” got accepted by IEEE TDSC.

• (2025.11) Our paper titled “MPMA: Preference Manipulation Attack Against Model Context Protocol” got accepted by AAAI 2026 (Oral).

• (2025.11) Our paper titled “Confguard: A Simple and Effective Backdoor Detection for Large Language Models” got accepted by AAAI 2026.