The 7th International Conference on Video, Signal and Image Processing (VSIP 2025)

Special Session 1: Secure Visual Models

Session Organizers


Prof. Zhiwu Wu, Hefei University, China
Asst. Prof. Mengyuan Liu, Peking University, China

Sepcial Session Topics

 

The topics of interest include, but are not limited to:
• Adversarial Attacks and Defenses in Visual Models
• Trustworthy and Robust Deep Vision Systems
• Privacy-preserving Visual Recognition
• Explainability and Interpretability in Secure Vision
• Secure Multi-modal Perception and Reasoning
• Visual Anomaly Detection in Open-world Settings
• Federated Learning for Secure Image and Video Analysis
• Benchmark Datasets and Evaluation for Visual Security

Submission Method


Submit your Full Paper (no less than 8 pages) or your paper abstract—without publication (200–400 words)—via the Online Submission System, then choose Special Session 2 (Secure Visual Models).

Template Download

Introduction of Session Organizers


Prof. Zhiwu Wu
Hefei University, China

Zhiwu Wu, Ph.D., received his doctorate from the University of Science and Technology of China in 2017 and is currently a Professor at Hefei University. His research interests lie in secure artificial intelligence and deep learning-driven visual perception computing. He has authored over 30 papers in top-tier journals and conferences, including IEEE Transactions on Image Processing (TIP), CVPR, ICCV, ACL, IEEE Transactions on Evolutionary Computation (TEVC), IEEE Transactions on Multimedia (TMM), Information Fusion, and Pattern Recognition. He also serves as a reviewer for several leading journals and conferences, such as TPAMI, TIP, TMM, TCSVT, TEVC, PR, AAAI, and IJCAI.

 

 

Asst. Prof. Mengyuan Liu
Peking University, China

Mengyuan Liu, Ph.D., is an Assistant Professor at the School of Information Engineering, Peking University. His research vision focuses on enabling robots to perceive and understand the human-centered physical world through visual intelligence, thereby facilitating natural, intuitive, and human-friendly human-computer interaction. He has published over 50 academic papers in top-tier international conferences such as CVPR, ECCV, AAAI, IJCAI, and ACM MM, as well as in leading journals including IEEE Transactions on Multimedia (TMM), IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), Pattern Recognition, and IEEE Transactions on Image Processing (TIP). His work has been cited more than 2,000 times, with a single paper receiving over 600 citations. He has been recognized as an ESI Highly Cited Researcher for three consecutive years.