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, we hypothesize that the gradient magnitude links to the
model robustness. Motivated by this, we propose to perturb both the image and
the label during training, which we call Bilateral Adversarial Training (BAT).
To generate the adversarial label, we derive an closed-form heuristic solution.
To generate the adversarial image, we use one-step targeted attack with the
target label being the most confusing class. In the experiment, we first show
that random start and the most confusing target attack effectively prevent the
label leaking and gradient masking problem. Then coupled with the adversarial
label part, our model significantly improves the state-of-the-art results. For
example, against PGD100 white-box attack with cross-entropy loss, on CIFAR10,
we achieve 63.7\% versus 47.2\%; on SVHN, we achieve 59.1\% versus 42.1\%. At
last, the experiment on the very (computationally) challenging ImageNet dataset
further demonstrates the effectiveness of our fast method.

本文提出了一种 Bilateral Adversarial Training 方法，使用一步定向攻击生成对抗样本来训练一个抗攻击性更强的神经网络，实验结果表明该方法对于对抗性攻击的鲁棒性有显著提升。