SmoothFool: An Efficient Framework for Computing Smooth Adversarial Perturbations

TL;DR

This paper introduces SmoothFool, a framework for generating smooth adversarial perturbations that reveal new vulnerabilities in deep neural networks, demonstrating their effectiveness and transferability against various defenses.

Contribution

The paper presents a novel, efficient method for creating smooth adversarial perturbations, expanding understanding of DNN vulnerabilities beyond traditional $ ext{l}_p$ bounds.

Findings

Smooth adversarial perturbations exist for common neural network architectures.

Smoothness increases the robustness of perturbations against defenses.

Smooth perturbations transfer better across data points and models.

Abstract

Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properties or frequency-domain characteristics has not been sufficiently explored. In this paper, we study the smoothness of perturbations and propose SmoothFool, a general and computationally efficient framework for computing smooth adversarial perturbations. Through extensive experiments, we validate the efficacy of the proposed method for both the white-box and black-box attack scenarios. In particular, we demonstrate that: (i) there exist extremely smooth adversarial perturbations for well-established and widely used network architectures, (ii) smoothness significantly enhances the robustness of perturbations against state-of-the-art defense mechanisms, (iii) smoothness improves the transferability of adversarial perturbations across both data points and network architectures, and (iv) class categories exhibit a variable range of susceptibility to smooth perturbations. Our results suggest that smooth APs can play a significant role in exploring the vulnerability extent of DNNs to adversarial examples.