Generative Adversarial Learning Neural Network Based Secure Data Transmission in Cognitive Radios

Abstract

In this paper, a communication model in cognitive radios is developed uses the machine learning to learn the dynamics of jamming attack in a cognitive radios. It is designed further to make their transmission decision which automatically adapts with the transmission dynamics in order to mitigate the launched jamming attacks. The Generative Adversarial Learning Neural Network (GALNN or GDNN) automatically learns with the synthesized training data (training) with a generator and discriminator type neural networks that encompasses minimax game theory.The elimination of the jamming attack is carried out with the assistance of the defence strategies and with increased detection rate in GAN.The GDNN with game theory is designed to validate the channel condition with the cross entropy loss function and back-propagation algorithm which improves the communication reliability in the network. The simulation is conducted in NS2.34 tool against several performance metrics in reducing the misdetection rate and false alarm rate. The results show that the GDNN obtains increased rate of successful transmission by taking optimal actions to acts as a defense mechanism to mislead the jammer, where jammer makes high misclassification errors on transmission dynamics.