Consistency Regularization for Adversarial Robustness

Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, a significant generalization gap in the robustness obtained from AT has been problematic, making practitioners to consider a bag of tricks for a successful training, e.g., early stopping. In this paper, we investigate data augmentation (DA) techniques to address the issue. In contrast to the previous reports in the literature that DA is not effective for regularizing AT, we discover that DA can mitigate overfitting in AT surprisingly well, but they should be chosen deliberately. To utilize the effect of DA further, we propose a simple yet effective auxiliary 'consistency' regularization loss to optimize, which forces predictive distributions after attacking from two different augmentations to be similar to each other. Our experimental results demonstrate that our simple regularization scheme is applicable for a wide range of AT methods, showing consistent yet significant improvements in the test robust accuracy. More remarkably, we also show that our method could significantly help the model to generalize its robustness against unseen adversaries, e.g., other types or larger perturbations compared to those used during training. Code is available at https://github.com/alinlab/consistency-adversarial.