Median-Krum: A Joint Distance-Statistical Based Byzantine-Robust Algorithm in Federated Learning
Francesco Colosimo, Floriano De Rango
Abstract
The wide spread of Artificial Intelligence-based services in recent years has encouraged research into new Machine Learning paradigms. Federated Learning (FL) represents a new distributed approach capable of achieving higher privacy and security guarantees than other methodologies since it allows multiple users to collaboratively train a global model without sharing their local training data. In this paper, an analysis of the characteristics of Federated Learning is therefore carried out, with a particular focus on security aspects. In detail, currently known vulnerabilities and their respective countermeasures are investigated, focusing on aggregation algorithms that provide robustness against Byzantine failures. Following this direction, Median-Krum is proposed as a new aggregation algorithm whose validity is observed on a set of simulations that recreate realistic scenarios, in the absence and presence of Byzantine adversaries. It combines the Distance-based Krum approach with the Statistical strategy of median based aggregation algorithm. Achieved results demonstrate the functionality of the proposed solutions in terms of accuracy and convergence rounds in comparison with FedAvg, Krum, Multi-Krum and FedMedian FL approaches under a correct and incorrect estimation of the attackers number.