Frequency-Selective Adversarial Attack Against Deep Learning-Based Wireless Signal Classifiers

Abstract

Although Deep learning (DL) provides state-of-art results for most spectrum sensing tasks, it is vulnerable to adversarial examples. Based on this phenomenon, we consider a noncooperative communication scenario where an intruder tries to recognize the modulation type of the intercepted signal. Specifically, this paper aims to minimize the intruder's accuracy while guaranteeing that the intended receiver can still recover the underlying message with the highest reliability. This process is implemented by adding adversarial perturbations to the channel input symbols at the encoder. In image classification, the perturbation is limited to be imperceptible to a human observer by minimizing the p norm, while in this work, we enriched the connotation of adversarial examples, and first proposed that the imperceptibility of adversarial examples in the field of wireless signals is the imperceptibility of filters. Based on this perspective, we optimized the model of adversarial examples and constrained the adversarial perturbation to a narrow frequency band so that filters cannot filter it out. We also define a new set of metrics to describe the imperceptibility of the wireless signal adversarial example. The simulation results demonstrate the viability of our approach in securing wireless communication against state-ofthe-art DL-based intruders while minimizing communication performance reduction.