A talk by Kaizhu Huang, professor and associate dean of research, School of Advanced Technology, Xian Jiaotong-Liverpool University (XJTLU); and founding director of Suzhou Key Lab of Cognitive Computation and Applied Technology, XJTLU.
The talk will be in English and is open to all members of the DKU community. A lunch box will be provided (first come, first served).
Adversarial examples are augmented data points generated by imperceptible perturbation of input samples. They have recently drawn much attention with the machine learning community. Being difficult to distinguish from real data, adversarial examples could change the prediction of many state-of-the-art deep learning models. Recent attempts have been made to build robust and safe models that consider adversarial examples. However, these methods can either lead to performance drops or are ad-hoc in nature and lack mathematic motivations. In this talk, we introduce the fundamental, present the interpretations, and propose a unified framework to build robust machine learning models against adversarial examples in a systematic way. Finally, we also harness adversarial examples and demonstrate a series of successful applications.
Kaizhu Huang is a professor at Xi’an Jiaotong-Liverpool University, China. He acts as associate dean of research in the School of Advanced Technology and is the founding director of Suzhou Municipal Key Laboratory of Cognitive Computation and Applied Technology. Huang obtained his Ph.D. from The Chinese University of Hong Kong (CUHK) in 2004. Between 2004 and 2012, he worked at the Fujitsu Research Centre, CUHK, the University of Bristol, the National Laboratory of Pattern Recognition, the Chinese Academy of Sciences.
Huang works in machine learning, neural information processing, and pattern recognition. He received the 2011 Asia Pacific Neural Network Society Young Researcher Award, and has received best paper or book awards five times. As of October 2019, he had published nine books and over 190 international research papers in 70-plus international journals including JMLR, Neural Computation, IEEE T-PAMI, IEEE T-NNLS, IEEE T-BME and IEEE T-Cybernetics, and at conferences including NeurIPS, IJCAI, SIGIR, UAI, CIKM, ICDM, ICML, ECML, CVPR. He serves as an associate editor or advisory board member at a number of journals and book series. He has been invited as a keynote speaker to more than 20 international conferences or workshops.
Registration closes at 12pm, Monday Sept. 14
For any questions, contact Ivy Xu at firstname.lastname@example.org.