I am Wen Xiangyu (温翔宇), a 2nd year Ph.D. candidate in the Department of Computer Science and Engineering at the Chinese University of Hong Kong (CUHK). Before this, I earned my Bachelor’s and Master’s Degrees under the supervision of Prof. Jiang Wei from the University of Electronic Science and Technology of China (UESTC). Currently, my research studies unfold within the CUHK REliable Computing Laboratory (CURE Lab.), under the expert guidance of Prof. XU Qiang.

My focus is primarily on handling safety issues and planning problems associated with large language models (LLMs), aiming to make them safe and compliant within an agent system. Before that, I have done some researches on security issues, such as backdoor attacks, adversarial attacks and watermarking, of DNN models for the discriminative tasks.