Reputation-Based Classification for Malicious User Detection in Cognitive Radio Networks

Cognitive radio technology has advanced beyond traditional radio systems to efficiently utilize underutilized spectrum. In cognitive radio, cooperative secondary users (CSUs) engage in cooperative spectrum sensing (CSS) to access available frequency bands, ensuring no interference with primary users (PUs). However, the performance of cognitive radio networks (CRNs) is significantly impacted by security threats such as malicious users (MUs), who mimic genuine CSUs and transmit false information to the fusion center (FC), degrading the system’s effectiveness. To address this challenge, we propose a reputation score based algorithm to distinguish between genuine CSUs and MUs. The reputation score serves as a classifier, effectively separating trustworthy CSUs from malicious ones. Extensive simulations are conducted to demonstrate the effectiveness of this approach.