Characterizing Model Robustness via Natural Input Gradients

Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training, which explicitly enforces models to perform well on perturbed examples. In this work, we show the surprising effectiveness of instead regularizing the gradient with respect to model inputs on natural examples only. Penalizing input Gradient Norm is commonly believed to be a much inferior approach. Our analyses identify that the performance of Gradient Norm regularization critically depends on the smoothness of activation functions, and are in fact extremely effective on modern vision transformers that adopt smooth activations over piecewise linear ones (eg, ReLU), contrary to prior belief. On ImageNet-1k, Gradient Norm training achieves > 90% the performance of state-of-the-art PGD-3 Adversarial Training} (52% vs.~56%), while using only 60% computation cost of the state-of-the-art without complex adversarial optimization. Our analyses also highlight the relationship between model robustness and properties of natural input gradients, such as asymmetric sample and channel statistics. Surprisingly, we find model robustness can be significantly improved by simply regularizing its gradients to concentrate on image edges without explicit conditioning on the gradient norm.

Aliasing is a Driver of Adversarial Attacks

Aliasing is a highly important concept in signal processing, as careful consideration of resolution changes is essential in ensuring transmission and processing quality of audio, image, and video. Despite this, up until recently aliasing has received very little consideration in Deep Learning, with all common architectures carelessly sub-sampling without considering aliasing effects. In this work, we investigate the hypothesis that the existence of adversarial perturbations is due in part to aliasing in neural networks. Our ultimate goal is to increase robustness against adversarial attacks using explainable, non-trained, structural changes only, derived from aliasing first principles. Our contributions are the following. First, we establish a sufficient condition for no aliasing for general image transformations. Next, we study sources of aliasing in common neural network layers, and derive simple modifications from first principles to eliminate or reduce it. Lastly, our experimental results show a solid link between anti-aliasing and adversarial attacks. Simply reducing aliasing already results in more robust classifiers, and combining anti-aliasing with robust training out-performs solo robust training on $L_2$ attacks with none or minimal losses in performance on $L_{\infty}$ attacks.