Countermeasures Against Adversarial Examples in Radio Signal Classification

Authors:
Publisher website
Google Scholar
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.
Funding Information
  • U.K. Engineering and Physical Sciences Research Council (EP/R006385/1, EP/N007840/1)
  • International Scientific Partnership Programme of King Saud University (ISPP-18-134(2))
  • CELTIC-NEXT European Collaborative Project AIMM (C2019/2-5)
  • UKRI Innovate U.K. (48160)

This publication has 5 references indexed in Scilit: