no code implementations • 2 Dec 2017 • Chanh Nguyen, Georgi Georgiev, Yujie Ji, Ting Wang
We believe that this work opens a new direction for designing adversarial input detection methods.
no code implementations • ICLR 2019 • Xinyang Zhang, Yifan Huang, Chanh Nguyen, Shouling Ji, Ting Wang
On the possibility side, we show that it is still feasible to construct adversarial training methods to significantly improve the resilience of networks against adversarial inputs over empirical datasets.