Enhancing Security and Efficiency: A Lightweight Federated Learning Approach

Recently, as big data and AI technology advance, data privacy and security are increasingly critical. Federated Learning (FL) has become a key solution in machine learning to address these concerns. In this paper, we present a secure and lightweight FL scheme. It employs masking and Secret Sharing (SS) to securely aggregate data from distributed clients, thereby reducing the demands of model training on system resources. The scheme also computes data similarity among clients to evaluate each client’s contribution, defending against challenges posed by malicious clients. This approach safeguards privacy, facilitates accurate model updates, and addresses the challenges of limited resources in edge computing environments. We subjected our framework to rigorous validation using MNIST datasets. Experimental outcomes unequivocally substantiate the efficacy of our proposed methodology.