Adaptive Trust Threshold Model Based on Reinforcement Learning in Cooperative Spectrum Sensing

Abstract

In cognitive radio systems, cooperative spectrum sensing (CSS) can effectively improve the sensing performance of the system. At the same time, it also provides opportunities for malicious users (MUs) to launch spectrum-sensing data falsification (SSDF) attacks. This paper proposes an adaptive trust threshold model based on a reinforcement learning (ATTR) algorithm for ordinary SSDF attacks and intelligent SSDF attacks. By learning the attack strategies of different malicious users, different trust thresholds are set for honest and malicious users collaborating within a network. The simulation results show that our ATTR algorithm can filter out a set of trusted users, eliminate the influence of malicious users, and improve the detection performance of the system.