Detection of Rogue RF Transmitters using Generative Adversarial Nets

Understanding and analyzing the radio frequency (RF) environment have become indispensable for various autonomous wireless deployments. To this end, machine learning techniques have become popular as they can learn, analyze and even predict the RF signals and associated parameters that characterize a RF environment. However, classical machine learning methods have their limitations and there are situations where such methods become ineffective. One such setting is where active adversaries are present and try to disrupt the RF environment through malicious activities like jamming or spoofing. In this paper we propose an adversarial learning technique for identifying rogue RF transmitters and classifying trusted ones by designing and implementing generative adversarial nets (GAN). The GAN exploits the in-phase (I) and quadrature imbalance (i.e., the IQ imbalance) present in all transmitters to learn the unique high dimensional features that can be used as “fingerprints” for identifying and classifying the transmitters. We implement a generative model that learns the sample space of the IQ values of the known transmitters and use the learned representation to generate fake signals that imitate the transmissions of the known transmitters. We program 8 universal software radio peripheral (USRP) software defined radios as trusted transmitters and collect over-the-air raw IQ data from them using a RTL-SDR in a laboratory setting. We also implement a discriminator model and show that the discriminator is able to discriminate between the trusted transmitters from fake ones with 99.9% accuracy. Finally, the trusted transmitters are classified using convolutional neural network (CNN) and fully connected deep neural networks (DNN). Results reveal that the CNN and DNN are able to correctly discriminate between the 8 trusted transmitters with 81.6% and 96.6% accuracies respectively.