Reviews: Are Labels Required for Improving Adversarial Robustness?

This paper combines the two and conducts adversarial training by applying the regularization term on unlabeled data. The theoretical and empirical analysis are new. However, some crucial points are not well addressed. It is observed that the proposed method (UAT) behaves differently on CIFAR10 and SVHN (Fig.1), wrt m. On CIFAR10, it outperforms others starting from m 4k.