Federated Learning Based Intelligent Spectrum Management for Secure Cognitive IoT Communications

Abstract

The increasing density of IoT devices has intensified spectrum scarcity and security challenges in modern wireless communication systems. Conventional spectrum allocation mechanisms are centralized, static, and vulnerable to privacy leakage and malicious attacks. This paper proposes a federated learning–based intelligent spectrum management framework for cognitive IoT networks. Unlike traditional centralized learning, the proposed approach enables distributed IoT nodes to collaboratively train a global spectrum decision model without sharing raw data, thereby preserving privacy and enhancing security. Each node locally learns spectrum availability patterns and interference characteristics, while a lightweight aggregation mechanism updates the global model. Simulation results show that the proposed framework improves spectrum utilization efficiency, reduces interference, and enhances communication security compared to centralized and non-intelligent spectrum management schemes.