Joint spectrum sensing and D2D communications in Cognitive Radio Networks using clustering and deep learning strategies under SSDF attacks

Abstract

In Spectrum Sensing and Data Falsification Attacks (SSDF), malicious Secondary Users (SUs) in Cognitive Radio Networks (CRNs) intentionally try to disrupt the global Cooperative Spectrum Sensing (CSS) decision for their self-benefit. Most existing works focus on mitigating the impact of SSDF attacks on CSS decisions. However, a small piece of work jointly studies the CSS and opportunistic data transmission under SSDF attacks in a single framework, but they have some limitations. The present work proposes joint CSS and SU data transmissions in Energy Harvesting-enabled CRNs under SSDF attacks. The present work uses the clustering strategy to isolate the malicious SUs from the honest set of SUs using reputation value and other attributes. The identified malicious and unfit SUs are restricted from opportunistic Device-to-Device (D2D) communication in CRNs. An Ensemble Learning strategy is proposed, which enhances the CSS reliability over the existing works by ∼36.91%, ∼25.00%, and ∼19.04%. Several network constraints guide the reliable SU transmissions in a hybrid framework under SSDF attacks to support the Quality-of-Services for both primary and secondary networks.