A secured federated learning system leveraging confidence score to identify retinal disease

Abstract

Federated learning is a distributed machine learning paradigm that enables multiple clients to collaboratively train a global model without sharing their local data. How- ever, federated learning is vulnerable to adversarial attacks, where malicious clients can manipulate their local updates to degrade the performance or compromise the privacy of the global model. To mitigate this problem, this paper proposes a novel method that reduces the influence of malicious clients based on their confidence. We conducted our experiments on the Retinal OCT dataset. The proposed technique significantly improves the global model’s precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC). Precision rises from 0.869 to 0.906, recall rises from 0.836 to 0.889, F1 score rises from 0.852 to 0.898, and AUC-ROC rises from 0.836 to 0.889.