When Image Forensics/Anti-forensics meets Adversarial Machine Learning

Speaker:Prof. Jiantao Zhou

Time: 2018-04-02 10:00-12:00

Location: 106 Lecture Hall, Institute of computer science & technology of Peking University

Abstract: Adversarial machine learning (ML) has been a hot research topic in ML community, showing that many state-of-the-art, sophistically designed ML algorithms can be easily fooled.  Meanwhile, image forensics and anti-forensics have been extensively studied in the multimedia security community for over a decade. In this talk, our recent work on SIFT keypoint removal/injection is used an example to demonstrate that adversarial ML is closely connected to image forensics from many aspects.

- Y. M. Li, J. T. Zhou, and A. Cheng, “SIFT Keypoint Removal via Directed Graph Construction for Color Images”, IEEE Trans. on Inf. Forensics and Security (T-IFS), vol. 12, no. 12, pp. 2971-2985, 2017.

- Y. M. Li, J. T. Zhou, A. Cheng, X. M. Liu, and Y. Y. Tang, “SIFT Keypoint Removal and Injection via Convex Relaxation”, IEEE Trans. on Inf. Forensics and Security (T-IFS), vol. 11, no. 8, pp. 1722-1735, 2016.

Bio: Jiantao Zhou (M’11) received the B.Eng. degree from the Department of Electronic Engineering, Dalian University of Technology, in 2002, the M.Phil. degree from the Department of Radio Engineering, Southeast University, in 2005, and the Ph.D. degree from the Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, in 2009. He held various research positions with the University of Illinois at Urbana–Champaign, the Hong Kong University of Science and Technology, and the McMaster University. He is currently an Associate Professor with the Department of Computer and Information Science, Faculty of Science and Technology, University of Macau. He holds four granted U.S. patents and two granted Chinese patents. His research interests include multimedia security and forensics, and multimedia signal processing. He has co-authored two papers that received the Best Paper Award at the IEEE Pacific-Rim Conference on Multimedia in 2007 and the Best Student Paper Award at the IEEE International Conference on Multimedia and Expo in 2016.