Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharing

TL;DR

This paper introduces Federated Knowledge Recycling (FedKR), a privacy-preserving federated learning method that uses synthetic data sharing to enhance security and performance across institutions.

Contribution

FedKR is a novel approach combining synthetic data generation with dynamic aggregation to improve privacy and model accuracy in federated learning.

Findings

FedKR achieves 4.24% higher accuracy than local training.

It enhances security by reducing privacy attack surfaces.

Effective in data-scarce scenarios.

Abstract

Federated learning has emerged as a paradigm for collaborative learning, enabling the development of robust models without the need to centralise sensitive data. However, conventional federated learning techniques have privacy and security vulnerabilities due to the exposure of models, parameters or updates, which can be exploited as an attack surface. This paper presents Federated Knowledge Recycling (FedKR), a cross-silo federated learning approach that uses locally generated synthetic data to facilitate collaboration between institutions. FedKR combines advanced data generation techniques with a dynamic aggregation process to provide greater security against privacy attacks than existing methods, significantly reducing the attack surface. Experimental results on generic and medical datasets show that FedKR achieves competitive performance, with an average improvement in accuracy of 4.24% compared to training models from local data, demonstrating particular effectiveness in data scarcity scenarios.