Security and Energy Management in Cooperative Spectrum Sensing

Abstract

The revolutionary concept of cognitive radio (CR) has been developed to address the issue of spectrum scarcity in wireless networks. Cooperative spectrum sensing is seen as a promising strategy to dramatically increase spectrum sensing performance in cognitive radio networks, but it is vulnerable to Spectrum sensing data falsification (SSDF) attacks. Existing security references have concentrated on ways to lessen the impact of a SSDF attacking, but these approaches have relied heavily on assumptions such as the attackers being a numerical minority and there being a trustworthy node for data fusion. This realisation inspires us to conduct a thorough examination of the SSDF attack and fusion centre (FC) techniques outside of these constraints. In particular, analysing complex harmful actions allows us to think about a generic SSDF attack model that is more general than the existing methods. According to this overview of attacks, the resultant condition renders the FC clear to attack. Based on these considerations, the ideal attack approach to maximise Bayes risk is examined for both the unknown and known fusion rule scenarios. Second, by casting it as a combinatorial optimisation issue, energy efficiency of cooperative sensing is discussed. In order to enhance the overall energy efficiency of system, a deep learning framework is built based on this formulation by combining graph neural network with reinforcement learning. The efficacy of this method has been demonstrated through simulation tests at varying network scales.