Guojia Li is currently a Ph.D. candidate in the School of Cyber Science and Engineering at Zhengzhou University, China. He received his B.S. and M.S. degrees from University of Electronic Science and Technology of China (UESTC). His research interests focus on AI security, federated learning security, and multimodal adversarial security. (ORCID: 0009-0001-2855-5433)
Mingyue Cao is a Master's student at the School of Cyber Science and Engineering, Zhengzhou University. She holds a Bachelor's degree in Computer Science from Henan University. Her research interests include neural network backdoor attacks, with a focus on developing novel attack paradigms in vision–language models to assess their real-world security risks. She is also exploring robust defense mechanisms against such threats.
Yihong Zhang is a Master's student at the School of Cyber Science and Engineering, Zhengzhou University. His research primarily focuses on security and adversarial attacks of self-supervised learning models. His current work involves designing adversarial examples in the absence of labels and studying the threat of model stealing attacks against pre-training models. Additionally, he is exploring the security challenges of these models in federated learning scenarios.
Simin Xu is a Master's student at the School of Cyber Science and Engineering, Zhengzhou University, where she also received her Bachelor's degree. Her research interests center on neural network backdoor attacks, with particular focus on developing stealthy trigger injection methods in data-scarce scenarios and analyzing their threats to real-world AI systems.
Yan Cao is currently an associate professor and doctoral supervisor at Zhengzhou University. He serves as a member of the Industrial Control Systems Information Security Professional Committee of the Chinese Association of Automation, a senior member of the China Computer Federation, and a member of the Big Data and Artificial Intelligence Expert Committee of Henan Province. His research focuses on cybersecurity and AI security.
