Recursive Euclidean Distance-based Robust Aggregation Technique for Federated Learning

Federated learning has gained popularity as a solution to data availability and privacy challenges in machine learning. However, the aggregation process of local model updates to obtain a global model in federated learning is susceptible to malicious attacks, such as backdoor poisoning, label-flipping, and membership inference. Malicious users aim to sabotage the collaborative learning process by training the local model with malicious data. This paper proposes a novel robust aggregation approach based on recursive Euclidean distance calculation. Our approach measures the Euclidean distance from the most recent global to local models and assigns weights accordingly. Local models which are far away from the most recent global model are assigned smaller weights to minimize the data poisoning effect during aggregation. Our experiments indicate that the proposed algorithm surpasses the latest algorithms by at least 5% in accuracy while reducing time complexity by less than 55%. Our contribution is significant as it addresses the critical issue of malicious attacks in federated learning while reducing aggregation time and improving the accuracy of the global model.