General

Wei Wang, Ph.D.
Professor (Associate)

Center for Research on Intelligent Perception and Computing (CRIPAC)
State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)
Institute of Automation, Chinese Academy of Sciences (CASIA)
Email: wei.wong@ia.ac.cn

Research Interests

  • Multimedia Privacy and Security. 1) Fake content detection, especially for Deepfakes with the intent to mislead; 2) Face anonymization, which aims to protect privacy-sensitive identity information of face video/image.

  • AI Safety. Problems in AI safety can be grouped into three categories: robustness, assurance, and specification. 1) Robustness guarantees that a system continues to operate within safe limits even in unfamiliar settings; 2) Assurance seeks to establish that it can be analyzed and understood easily by human operators; and 3) Specification is concerned with ensuring that its behavior aligns with the system designer's intentions.

  • Other Computer Vision, Pattern Recognition, or Machine Learning related topics.



Opportunities for Students

There is one opening available for master students starting Summer 2023. The ideal applicant is self-motivated and has strong skills in both mathematics and programming. The candidate is expected to have a strong interest in computer vision, and experience on face-related research is preferred. Please email me with your CV if you are interested in this opportunitiy.

Experience

​Dr. Wei Wang received his PhD degree in Pattern Recognition from the Institute of Automation, Chinese Academy of Sciences (CASIA) in 2012. He is currently an Associate Professor of the Center for Research on Intelligent Perception and Computing (CRIPAC), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA. He is a senior member of CCF, CSIG, etc. He is also a member of technical executive committee on Digital Forensics and Security of CSIG, technical committee (TC) on Computer Vision of CCF, TC on Pattern Recognition of CAAI, etc. His current research interests include artificial intelligence and its security problem, image and video forensics and steganalysis, and information content security. Dr. Wei Wang has published more than 80 research papers on these topics in refereed international journals and conferences including IEEE trans, CVPR, AAAI, ACM MM, etc.


Selected Publications

[1] Dongze Li, Wei Wang*, Kang Zhao, Jing Dong and Tieniu Tan, “RiDDLE: Reversible and Diversified De-Identification With Latent Encryptor,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8093–8102, 2023.

[2] Ziwen He, Wei Wang*, Jing Dong and Tieniu Tan, “Temporal Sparse Adversarial Attack on Sequence-Based Gait Recognition,” Pattern Recognition, vol. 133, p. 109028, Sep. 2023.

[3] Ziwen He, Wei Wang*, Jing Dong and Tieniu Tan, “Transferable Sparse Adversarial Attack,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14963–14972, 2022.

[4] Dongze Li, Wei Wang*, Hongxing Fan and Jing Dong, “Exploring Adversarial Fake Images on Face Manifold,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) , pp. 5785–5794, 2021.

[5] Ziwen He, Wei Wang*, Weinan Guan, Jing Dong and Tieniu Tan, “Defeating DeepFakes via Adversarial Visual Reconstruction,” in Proceedings of the 30th ACM International Conference on Multimedia, 2022.

[6] Wei Wang, Jing Dong, Ziwen He and Zhenan Sun, “A Brief Introduction to Visual Adversarial Samples,” Journal of Cyber Security, vol. 5, no. 2, pp. 39–48, 2020.

[7] Bo Peng, Wei Wang*, Jing Dong and Tieniu Tan, “Image Forensics Based on Planar Contact Constraints of 3D Objects,” IEEE Transactions on Information Forensics and Security, vol. 13, no. 2, pp. 377–392, Feb. 2018.

[8] Bo Peng, Wei Wang*, Jing Dong and Tieniu Tan, “Optimized 3D Lighting Environment Estimation for Image Forgery Detection,” IEEE Transactions on Information Forensics and Security, vol. 12, no. 2, pp. 479–494, Feb. 2017.

[9] Bo Wang, Mengnan Zhao, Wei Wang*, Fei Wei, Zhan Qin and Kui Ren, “Are You Confident That You Have Successfully Generated Adversarial Examples?,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 6, pp. 2089–2099, Jun. 2021.

[10] Bo Wang, Mengnan Zhao, Wei Wang*, Xiaorui Dai, Yi Li and Yanqing Guo, “Adversarial Analysis for Source Camera Identification,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 11, pp. 4174–4186, 2021.