Threats of Adversarial Attacks in DNN-Based Modulation Recognition

摘要

With the emergence of the information age, mobile data has become more random, heterogeneous and massive. Thanks to its many advantages, deep learning is increasingly applied in communication fields such as modulation recognition. However, recent studies show that the deep neural networks (DNN) is vulnerable to adversarial examples, where subtle perturbations deliberately designed by an attacker can fool a classifier model into making mistakes. From the perspective of an attacker, this study adds elaborate adversarial examples to the modulation signal, and explores the threats and impacts of adversarial attacks on the DNN-based modulation recognition in different environments. The results show that, regardless of a white-box or a black-box model, the adversarial attack can reduce the accuracy of the target model. Among them, the performance of the iterative attack is superior to the one-step attack in most scenarios. In order to ensure the invisibility of the attack (the waveform being consistent before and after the perturbations), an appropriate perturbation level is found without losing the attack effect. Finally, it is attested that the signal confidence level is inversely proportional to the attack success rate, and several groups of signals with high robustness are obtained.