Research Article
HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning
@INPROCEEDINGS{10.1007/978-3-031-73699-5_1, author={Sheraz Ali and Saqib Mamoon and Areeba Usman and Zain ul Abidin and Chuan Zhao}, title={HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning}, proceedings={Security and Privacy in New Computing Environments. 6th International Conference, SPNCE 2023, Guangzhou, China, November 25--26, 2023, Proceedings}, proceedings_a={SPNCE}, year={2025}, month={1}, keywords={Machine Learning Collaborative Machine Learning Privacy-Preserving Federated Learning Homomorphic Encryption Secure Multiparty Computation Secret Sharing Differential Privacy}, doi={10.1007/978-3-031-73699-5_1} }- Sheraz Ali
Saqib Mamoon
Areeba Usman
Zain ul Abidin
Chuan Zhao
Year: 2025
HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning
SPNCE
Springer
DOI: 10.1007/978-3-031-73699-5_1
Abstract
In this study, we introduce a novel Hybrid Federated Learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated Learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees.
