PPSFL: Privacy-preserving Split Federated Learning via Functional Encryption
In this paper, we propose a novel and efficient privacy-preserving split federated learning (PPSFL) framework, that achieves both privacy protection and model accuracy with reasonable computational and communication cost. We describe the implementations of PPSFL on Multi-layer Perceptron (MLP) and Convolutional Neural Network (CNN) models with distributed clients to evaluate the performance of PPSFL.
National Natural Science Foundation of China under grant number 62072356
Email Address of Submitting Authorjing.firstname.lastname@example.org
ORCID of Submitting Author0000000252173910
Submitting Author's InstitutionXidian University
Submitting Author's Country