A chaotic maps-based privacy-preserving distributed deep learning for incomplete and Non-IID datasets
This addresses privacy and data heterogeneity challenges in federated learning for applications with sensitive datasets, but it appears incremental as it builds on existing methods.
The authors tackled the problem of training deep learning models on sensitive, non-IID data in federated learning by comparing differential privacy with chaotic-based encryption for enhanced privacy, resulting in improved average performance metrics even with non-IID data.
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.