Jianyu Wang

Mitigating Adversarial Effects Through Randomization

2017 · arXiv (Cornell University)

Convolutional neural networks have demonstrated high accuracy on various tasks in recent years. However, they are extremely vulnerable to adversarial examples. For example, imperceptible perturbations added to clean images can cause convolutional neural networks to …

Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks

2019

In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training [34], we hypothesize that the gradient magnitude links to the model …