Enhancing IoT-Based smart city security through federated learning and privacy preservation using FedAC algorithm

In day today life IoT devices in smart city infrastructures are increasing rapidly, so security plays a vital role in safeguarding IoT devices against new cyber threats. This treatise presents the Federated Adaptive Clustering (FedAC) algorithm, an innovative and novel method designed to enhance IoT-based smart city security through federated learning and privacy preservation. FedAC employs an adaptive clustering technique to group edge devices based on data proximity, computational and computing power, thereby optimising local training and minimising communication overhead. The methodology guarantees robust data privacy by integrating differential privacy and safe multi-party computation within each cluster. The dynamic re-clustering feature adapts to changing data distributions and device availability, maintaining high model performance and efficiency. Real-world datasets demonstrate that FedAC achieves 92.5% accuracy while reducing communication overhead by 35% compared to traditional federated learning algorithms. Privacy loss is kept minimal with a privacy budget (epsilon) of 1.0, and operational effectiveness and performance are improved by 25% in convergence time. These findings highlight the potential of FedAC in enhancing smart city security, providing a scalable and resilient federated learning framework well-suited to the complexities of IoT environments.