Intra-Class Universal Adversarial Attacks on Deep Learning-Based Modulation Classifiers

• Published in: IEEE communications letters Vol. 27; no. 5; p. 1
• Main Authors: Li, Ruiqi, Liao, Hongshu, An, Jiancheng, Yuen, Chau, Gan, Lu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.05.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adversarial attacks; Algorithms; Classifiers; deep learning; Eavesdropping; Jamming; Machine learning; Modulation; modulation classification; Perturbation; Perturbation methods; Receivers; Robustness (mathematics); Signal classification; Synchronization; Threat models; Transmitters; universal adversarial attacks; Wireless communication; wireless security
• ISSN: 1089-7798; 1558-2558
• DOI: 10.1109/LCOMM.2023.3261423

Most existing adversarial attack methods generally rely on ideal assumptions, which is unreasonable for practical applications. In this paper, a practical threat model which utilizes adversarial attacks for anti-eavesdropping is proposed and a physical intra-class universal adversarial perturbation (IC-UAP) crafting method against DL-based wireless signal classifiers is then presented. First, an IC-UAP algorithm is proposed based on the threat model to craft a stronger UAP attack against the samples in a given class from a batch of samples in the class. Then, we develop a physical attack algorithm based on the IC-UAP method, in which perturbations are optimized under random shifting to enhance the robustness of IC-UAPs against the unsynchronization between adversarial attacks and attacked signals. Finally, the numerical results corroborate the effectiveness of the proposed approach based on the benchmark dataset.