A chaotic maps-based privacy-preserving distributed deep learning for incomplete and Non-IID datasets

TL;DR

This paper addresses privacy-preserving distributed deep learning over incomplete and non-IID data in a federated setting. It evaluates two privacy techniques, differential privacy and chaotic maps-based encryption, within a methodological framework that shares missing-feature distributions to enable imputation and uses Federated Averaging for model aggregation. Across three healthcare datasets, the experiments show that federated learning consistently improves performance metrics, while incorporating privacy layers yields results that are largely comparable to the non-private baseline. The findings suggest that privacy-preserving FL can achieve strong accuracy in realistic non-IID and incomplete-data scenarios, making it suitable for sensitive domains like healthcare.

Abstract

Federated Learning is a machine learning approach that enables the training of a deep learning model among several participants with sensitive data that wish to share their own knowledge without compromising the privacy of their data. In this research, the authors employ a secured Federated Learning method with an additional layer of privacy and proposes a method for addressing the non-IID challenge. Moreover, differential privacy is compared with chaotic-based encryption as layer of privacy. The experimental approach assesses the performance of the federated deep learning model with differential privacy using both IID and non-IID data. In each experiment, the Federated Learning process improves the average performance metrics of the deep neural network, even in the case of non-IID data.