Maximizing Interweave CRNs Throughput Under SSDF Attacks: A DRL-Enabled POMDP Approach.

This work addresses the threat of Spectrum Sensing Data Falsification (SSDF) attacks in interweave Cognitive Radio Networks (CRNs), which manipulate the spectrum sensing process and consequently affect the overall performance and reliability of CRNs. We exploit passive and active Reconfigurable Intelligent Surfaces (RIS) to counter these issues and enhance signal integrity and data delivery. We adopt a Partially Observable Markov Decision Process (POMDP) framework to increase the spectrum efficiency. We propose a Belief Aware Reinforcement Learning (BARL) algorithm to maximize the effective data rate in CRNs while addressing multiple constraints under SSDF attacks.