A Blockchain and Federated Learning Based Cooperative Spectrum Sensing Model for Cognitive Radio Networks

To address the issues of single point of failure and malicious attacks faced by existing federated learning-based spec-trum sensing models in cognitive radio, a cooperative spectrum sensing model based on blockchain and federated learning is proposed. A novel consensus mechanism based on Proof of Rapid Aggregation (PoRA) is first introduced, which effectively avoids the block generation delay caused by the mining process. Additionally, an adaptive weight aggregation algorithm is proposed using smart contract to improve accuracy. Experimental results demonstrate that the proposed model achieves efficient and accurate cooperative spectrum sensing while ensuring security.