Developing a Robust Defensive System against Adversarial Examples Using Generative Adversarial Networks

Abstract

In this work, we propose a novel defense system against adversarial examples leveraging the unique power of Generative Adversarial Networks (GANs) to generate new adversarial examples for model retraining. To do so, we develop an automated pipeline using combination of pre-trained convolutional neural network and an external GAN, that is, Pix2Pix conditional GAN, to determine the transformations between adversarial examples and clean data, and to automatically synthesize new adversarial examples. These adversarial examples are employed to strengthen the model, attack, and defense in an iterative pipeline. Our simulation results demonstrate the success of the proposed method.