Federated Learning (FL) has emerged as a prominent branch of Machine Learning due to the increasing prevalence of mobile computing and IoT technologies. Unlike centralized systems, in FL the devices often operate beyond the confines of centralized protection mechanisms. Consequently, the adoption of this methodology gives rise to various security concerns, including data leakage, communication vulnerabilities, and poisoning. In this paper we propose new distance-statistical aggregation algorithms that provide robustness against Byzantine failures, and we compare them with the well-known FedAvg on a set of simulations that recreate realistic scenarios. Achieved results demonstrate the functionality of the solutions in terms of efficiency and accuracy.
|