Chained Dual-GAN: A Generalized Defense against Adversarial Attacks

Abstract

Neural networks play a significant role in the field of image classification. When an input image is modified by adversarial attacks, the changes are imperceptible to the human eye, but it still leads to misclassification of the images. In this paper, we create a new approach to defend against adversarial attacks, dubbed Chained Dual-GAN (CD-GAN) that tackles the defense against adversarial attacks by minimizing the perturbations of the adversarial image using iterative undersampling and oversampling.