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

Applying for Postgraduate Admission (2026 Entry)

The M.S.E./M.E. in Artificial Intelligence Program includes specialized, intensive training in programming, AI and scientific paper writing. There are opportunities to do both the group and individual projects with leading companies working on applications of AI.

The invovled topics are:

1. AI Safety;
2. Multimedia Privacy and Security;
3. Other Pattern Recognition, Computer Vision, or Machine Learning related topics.

Timeline

• Application Start Date: 12 August 2025
• Early Application Deadline: 18 August 2025
• Normal Application Deadline: 28 September 2025

 Early applications are strongly encouraged.

• Late applications may only be considered on a space-available basis.
• Priority may be given to on-time applications.
• The admission quota may vary in different school year.

Requirements

The ideal candidates should:

• be self-motivated;
• have a strong interest in computer vision or generative AI;
• possess knowledge of linear algebra, calculus, probability theory, and introductory statistics;
• have strong programming skills;
• and demonstrate curiosity, critical thinking, and a willingness to unlearn and relearn.

Applicants should fulfill the following minimum English proficiency requirement:

• an overall band score of 6.5 in International English Language Testing System (IELTS); or
• a score of 550 in the China's College English Test Band 6 (CET-6); or
• other equivalent qualifications.

Contact

If you have further questions regarding the degree which are not answered here or elsewhere on the website, please contact me for the M.S.E./M.E. in Artificial Intelligence at wei.wong [at] ia.ac.cn.

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 New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), CASIA. He serves as Secretary-General of the Technical Committee on Digital Forensics and Security under the China Society of Image and Graphics (CSIG). He is also a senior member of CCF, CSIG, 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 100 research papers on these topics in mainstream refereed international journals and conferences including IEEE trans, ICML, CVPR, AAAI, ACM MM, etc.

1. Han, X.X., Yang, S.L., Wang, W., Li, Y., & Dong, J. (2025). Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time. ICML 2025, Accepted.
2. Guan, W., Wang, W., Peng, B., He, Z.W., Dong, J., & Cheng, H.N. (2025). Noise-Informed Diffusion-Generated Image Detection with Anomaly Attention. IEEE Transactions on Information Forensics and Security, Accepted.
3. Guan, W., Wang, W., Dong, J., & Peng, B. (2024). Improving Generalization of Deepfake Detectors by Imposing Gradient Regularization. IEEE Transactions on Information Forensics and Security, 19, 5345–5356.
4. Han, X., Yang, S., Wang, W., He, Z., & Dong, J. (2024). Exploiting Backdoors of Face Synthesis Detection with Natural Triggers. ACM Transactions on Multimedia Computing, Communications, and Applications. 
5. Li, D., Zhao, K., Wang, W., Peng, B., Zhang, Y., Dong, J., & Tan, T. (2024). AE-NeRF: Audio Enhanced Neural Radiance Field for Few Shot Talking Head Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 3037–3045. 
6. Zhao, M., Zhang, L., Wang, W., Kong, Y., & Yin, B. (2024). Adversarial Attacks on Scene Graph Generation. IEEE Transactions on Information Forensics and Security, 19, 3210–3225.
7. Yang, S., Wang, W., Lan, Y., Fan, X., Peng, B., Yang, L., & Dong, J. (2024). Learning Dense Correspondence for NeRF-Based Face Reenactment. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 6522–6530. 
8. Yang, S., Wang, W., Ling, J., Peng, B., Tan, X., & Dong, J. (2023). Context-Aware Talking-Head Video Editing. Proceedings of the 31st ACM International Conference on Multimedia, 7718–7727. 
9. Yang, S., Wang, W., Peng, B., & Dong, J. (2023). Designing a 3D-Aware StyleNeRF Encoder for Face Editing. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
10. He, Z., Wang, W., Dong, J., & Tan, T. (2023). Temporal sparse adversarial attack on sequence-based gait recognition. Pattern Recognition, 133, 109028.
11. Zhao, M., Wang, B., Wang, W., Kong, Y., Zheng, T., & Ren, K. (2022). Guided Erasable Adversarial Attack (GEAA) Toward Shared Data Protection. IEEE Transactions on Information Forensics and Security, 17, 2468–2482. 
12. He, Z., Wang, W., Guan, W., Dong, J., & Tan, T. (2022). Defeating DeepFakes via Adversarial Visual Reconstruction. Proceedings of the 30th ACM International Conference on Multimedia, 2464–2472.
13. Li, D., Wang, W., Fan, H., & Dong, J. (2021). Exploring Adversarial Fake Images on Face Manifold. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 5785–5794. 
14. Wang, W., Dai, X., Li, Y., & Guo, Y. (2021). Adversarial Analysis for Source Camera Identification. IEEE Transactions on Circuits and Systems for Video Technology, 31(11), 4174–4186. 
15. Wang, B., Zhao, M., Wang, W., Wei, F., Qin, Z., & Ren, K. (2021). Are You Confident That You Have Successfully Generated Adversarial Examples? IEEE Transactions on Circuits and Systems for Video Technology, 31(6), 2089–2099.