Adversarial Training for Deep Learning: A Framework for Improving Robustness, Generalization and Interpretability
Zhanxing Zhu, Peking University
2019-11-13 16:00:00 ~ 2019-11-13 17:30:00
Room 310, Yi Fu Building
Weinan Zhang, Assistant Professor, John Hopcroft Center for Computer Science
In this talk, I will introduce various approaches for how to construct adversarial examples. Then I will present a framework, named as adversarial training, for improving robustness of deep networks to defense the adversarial examples. Two approaches will be introduced for accelerating adversarial training from perspective of optimal control theory. We also discover that adversarial training could help to enhance the interpretability of CNNs. 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 recent works of my group on NeurIPS, ICML, CVPR and ICLR (under review).