学术会议
学术会议

学术会议

您当前的位置: 首页> 学术会议
20191106 Zhanxing Zhu:Adversarial Training for Deep Learning: A Framework for Improving Robustness and Generalization
时间:2019-11-05

报告时间:2019.11.6日下午15:00-16:00
报告地点:明德主楼1016

报告题目:Adversarial Training for Deep Learning: A Framework for Improving Robustness and Generalization


报告摘要:Deep learning has achieved tremendous success in various application areas. Unfortunately, recent works show that an adversary is able to fool the deep learning models into producing incorrect predictions by manipulating the inputs maliciously. The corresponding manipulated samples are called adversarial examples. This vulnerability issue dramatically hinders the deployment of deep learning, particularly in safety-critical applications.

In this talk, I will introduce various approaches for how to construct adversarial examples, and show how to understand and enhance the transferability of adversarial examples. Then I will present a framework, named as adversarial learning, for improving robustness of deep networks to defense the adversarial examples. Also I will introduce two approaches for accelerating adversarial training from perspective of optimal control theory. Moreover, I will show that the introduced adversarial learning framework can be extended as an effective regularization strategy to improve the generalization in semi-supervised learning. 

This talk will cover my group’s papers on NeurIPS, ICML and CVPR.

报告人简介:Dr. Zhanxing Zhu, is currently  assistant professor at School of Mathematical Sciences, Peking University, also affiliated with Center for Data Science, Peking University. He obtained Ph.D degree in  machine learning from University of Edinburgh in 2016. His research interests cover machine learning and its applications in various domains.  Currently he mainly focuses on deep learning theory and optimization algorithms, reinforcement learning, and applications in traffic, computer security, computer graphics, medical and healthcare etc. He has published more than 40 papers on top AI journals and conferences, such as NIPS, ICML, CVPR, ACL, IJCAI, AAAI, ECML etc.  He was awarded “2019 Alibaba Damo Young Fellow”, and obtained “Best Paper Finalist” from the top computer security conference CCS 2018.