Defending Wireless Receivers Against Adversarial Attacks on Modulation Classifiers

Abstract

Deep learning has been adopted for a wide range of wireless communication tasks, including modulation classification, because of its great classification capability. However, deep learning models have been shown to also introduce risks and vulnerabilities. For instance, adversarial attacks craft and introduce imperceptible perturbations that compromise the accuracy of deep learning-based modulation classifiers on wireless receivers. Therefore, in this paper, we propose a novel wireless receiver architecture that enhances deep learning-based modulation classifiers to defend them against adversarial attacks. Our experimental results show that our defense technique significantly diminishes the accuracy reduction that is caused by adversarial attacks by protecting modulation classifiers at least 18% more than existing defense techniques.