Zhou Yuguang (周宇光)

About Me

I am a Ph.D student in HKUST, advised by Prof. Shuai Wang. Before this, I obtained my bachelor's degree at Beihang University and conducted research on AI adversarial attacks under the supervision of Prof. Aishan Liu. I earned my master's degree at National University of Singapore, where I studied data protection and privacy issues of large language models with Prof. Jiaheng Zhang. I also interned at ByteDance Singapore. My research interest mainly lies in LLM-based agent safety, foundation model data privacy and large model interpretability.

Education

• Ph.D. in Computer Science and Engineering, HKUST (ongoing)
• M.Sc. in Data Science and Machine Learning, NUS
• B.S. in Artificial Intelligence, Beihang University

Publications

• Prompt inversion attack against collaborative inference of large language models
  Wenjie Qu*, Yuguang Zhou*, Yongji Wu*, Tingsong Xiao, Binhang Yuan, Yiming Li, Jiaheng Zhang
  IEEE Symposium on Security and Privacy 2025
• Compromising Embodied Agents with Contextual Backdoor Attacks
  Aishan Liu*, Yuguang Zhou*, Xianglong Liu, Tianyuan Zhang, Siyuan Liang, Jiakai Wang, Yanjun Pu, Tianlin Li, Junqi Zhang, Wenbo Zhou, Qing Guo and Dacheng Tao
  IEEE Transactions on Information Forensics and Security
• Pre-trained trojan attacks for visual recognition
  Aishan Liu, Xianglong Liu, Xinwei Zhang, Yisong Xiao, Yuguang Zhou, Siyuan Liang, Jiakai Wang, Xiaochun Cao, Dacheng Tao
  International Journal of Computer Vision