“As AI outperforms human in more and more tasks, the vulnerabilities of AI itself, such as trojan/backdoor/adversarial sample, becomes a more and more serious concern.”
Leo Yu Zhang (M’17) received the bachelor’s and master’s degrees in computational mathematics from Xiangtan University, Xiangtan, China, in 2009 and 2012, respectively, and the Ph.D. degree from the City University of Hong Kong, Hong Kong, in 2016. He is currently a Lecturer with the School of Information Technology, Deakin University, VIC, Australia. He held various research positions with the City University of Hong Kong, the University of Macau, Macau, China, the University of Ferrara, Ferrara, Italy, and the University of Bologna, Bologna, Italy. His current research interests include AI-related security, applied cryptography and differential privacy. He has published more than 50 research papers in refereed venues, including IEEE TDSC, TMM, etc., with a citation over 1,200 and H-index 18 according to Google scholar.