Implicit Bias of Adversarial Training for Deep Neural Networks

no code implementations • ICLR 2022 • Bochen Lv, Zhanxing Zhu

Furthermore, we generalize this result to the case of adversarial training for non-linear homogeneous deep neural networks without the linear separability of the dataset.

A frequency domain analysis of gradient-based adversarial examples

no code implementations • 1 Jan 2021 • Bochen Lv, Pu Yang, Zehao Wang, Zhanxing Zhu

And the log-spectrum difference of the adversarial examples and clean image is more concentrated in the high-frequency part than the low-frequency part.