Radio Attack Detection Using Deep Learning Techniques

The marked rise of wireless devices and the Internet of Things devices has increased the demand for wireless spectrum, leading to spectrum scarcity. Cognitive Radio Networks (CRNs) enable secondary users (SUs) to use the underutilized and unused frequency bands but are vulnerable to security threats like Byzantine and Primary User Emulation (PUE) attacks, disrupting spectrum sensing. In this work investigates use of a novel integrated spectrum sensing algorithm combining weighted sensing with Deep Q-Networks (DQN) and Generative Adversarial Networks (GAN) to optimize spectrum utilization and counteract these attacks. By using these methods can enhanced robustness against security threats, contributing advancement of CRN technologies implemented in Googlecolab and validated in MATLAB, the experimental analysis demonstrates integrated algorithm significantly outperforms basic weighted algorithm, integrated weighted algorithm got highest accuracy 99.03%.