On Model Robustness Against Adversarial Examples

Abstract

We study the model robustness against adversarial examples, referred to as small perturbed input data that may however fool many state-of-the-art deep learning models. Unlike previous research, we establish a novel theory addressing the robustness issue from the perspective of stability of the loss function in the small neighborhood of natural examples. We propose to exploit an energy function to describe the stability and prove that reducing such energy guarantees the robustness against adversarial examples. We also show that the traditional training methods including adversarial training with the $l_2$ norm constraint (AT) and Virtual Adversarial Training (VAT) tend to minimize the lower bound of our proposed energy function. We make an analysis showing that minimization of such lower bound can however lead to insufficient robustness within the neighborhood around the input sample. Furthermore, we design a more rational method with the energy regularization which proves to achieve better robustness than previous methods. Through a series of experiments, we demonstrate the superiority of our model on both supervised tasks and semi-supervised tasks. In particular, our proposed adversarial framework achieves the best performance compared with previous adversarial training methods on benchmark datasets MNIST, CIFAR-10, and SVHN. Importantly, they demonstrate much better robustness against adversarial examples than all the other comparison methods.