Generating adversarial examples with elastic-net regularized boundary equilibrium generative adversarial network

摘要

To improve the attack success rate and image perceptual quality of adversarial examples against deep neural networks(DNNs), we propose a new Generative Adversarial Network (GAN) based attacker, named Elastic-net Regularized Boundary Equilibrium Generative Adversarial Network(ERBEGAN). Recent studies have shown that DNNs are easy to attack by adversarial examples(AEs) where benign images with small-magnitude perturbations mislead DNNs to incorrect results. A number of methods are proposed to generate AEs, but how to generate them with high attack success rate and perceptual quality needs more effort. Most attackers generate AEs by restricting L-2-norm and L-infinity-norm of adversarial perturbations. However, very few works have been developed on L-1 distortion matrix which encourages sparsity in the perturbation. In this paper, we penalize both L-2-norm and L-1-norm of perturbation as Elastic-Net regularization to improve the diversity and robustness of AEs. We further improve GAN by minimizing the additional pixel-wise loss derived from the Wasserstein distance between benign and adversarial auto-encoder loss distributions. Extensive experiments and visualizations on several datasets show that the proposed ER-BEGAN can yield higher attack success rates than the state-of-the-art GAN-based attacker AdvGAN under the semi-whitebox and black-box attack settings. Besides, our method efficiently generates diverse adversarial examples that are more perceptually realistic. (c) 2020 Elsevier B.V. All rights reserved.