Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems

Abstract

Deep Neural Networks (DNNs) have become prevalent in wireless communication systems due to their promising performance. However, similar to other DNN-based applications, they are vulnerable to adversarial examples. In this work, we propose an input-agnostic, undetectable, and robust adversarial attack against DNN-based wireless communication systems in both white-box and black-box scenarios. We design tailored Universal Adversarial Perturbations (UAPs) to perform the attack. We also use a Generative Adversarial Network (GAN) to enforce an undetectability constraint for our attack. Furthermore, we investigate the robustness of our attack against countermeasures. We show that in the presence of defense mechanisms deployed by the communicating parties, our attack performs significantly better compared to existing attacks against DNN-based wireless systems. In particular, the results demonstrate that even when employing well-considered defenses, DNN-based wireless communications are vulnerable to adversarial attacks.

References in corpus (8)

• Over the Air Deep Learning Based Radio Signal Classification
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
• An Iterative BP-CNN Architecture for Channel Decoding
• Fast Deep Learning for Automatic Modulation Classification
• RNN Decoding of Linear Block Codes
• Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers
• Deep-Waveform: A Learned OFDM Receiver Based on Deep Complex-valued Convolutional Networks
• Effects of Forward Error Correction on Communications Aware Evasion Attacks