Countermeasures Against Adversarial Examples in Radio Signal Classification

TL;DR

This paper introduces a novel neural rejection-based countermeasure with label smoothing and noise injection to detect and reject adversarial examples in deep learning-based radio signal classification, enhancing security.

Contribution

It presents the first countermeasure against adversarial attacks in modulation classification, combining neural rejection, label smoothing, and Gaussian noise injection.

Findings

High accuracy detection and rejection of adversarial examples

Effective protection of deep-learning modulation classifiers

First application of such countermeasures in radio signal classification

Abstract

Deep learning algorithms have been shown to be powerful in many communication network design problems, including that in automatic modulation classification. However, they are vulnerable to carefully crafted attacks called adversarial examples. Hence, the reliance of wireless networks on deep learning algorithms poses a serious threat to the security and operation of wireless networks. In this letter, we propose for the first time a countermeasure against adversarial examples in modulation classification. Our countermeasure is based on a neural rejection technique, augmented by label smoothing and Gaussian noise injection, that allows to detect and reject adversarial examples with high accuracy. Our results demonstrate that the proposed countermeasure can protect deep-learning based modulation classification systems against adversarial examples.