Defense against PUE Attacks in DSA Networks using GAN based Learning

Primary user emulation (PUE) attacks can pose a significant threat to the deployment of a robust cognitive radio network implementing dynamic spectrum access, for an intelligent allocation and usage of already crowded spectrum bands. In this paper, we present a solution towards the PUE attacks. We present two generative adversarial net (GAN) based models to successfully emulate the primary users (PUs) in two ways. We propose a (i) dumb generator model without any "prior" knowledge of PU's feature space, (ii) a smart generator model with some "prior" knowledge about PU's transmission. We also propose two deep neural network based discriminator models to discriminate between the PU and the emulated primary users (EPU) from the corresponding generators. Both the generator and discriminator of each GAN model gets smarter with iterative and sequential GAN training. Through a testbed evaluation, we show that discriminators are able to catch similar to 50% of PUE attackers without the GAN training during the deployment phase. We also observe 100% accuracy for both the GAN models during training phase. Ultimately, after the GAN training, the discriminators achieved 98% and 99.5% accuracies, for dumb and smart generator models respectively, to distinguish "yet to be seen" PUE attacker.