PEPFL:A framework for a practical and efficient privacy-preserving federated learning  

作　　者：Yange Chen Baocang Wang Hang Jiang Pu Duan Yuan Ping Zhiyong Hong 

机构地区：[1]State Key Laboratory of Integrated Service Networks,Xidian University,Xi'an,710071,China [2]School of Information Engineering,Xuchang University,Xuchang,461000,China [3]School of Telecommunications Engineering,Xidian University,Xi'an,710071,China [4]Secure Collaborative Intelligence Laboratory,Ant Group,Hangzhou,310000,China [5]Facility of Intelligence Manufacture,Wuyi University,Jiangmen,529020,China

出　　处：《Digital Communications and Networks》2024年第2期355-368,共14页数字通信与网络（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant No.U19B2021;the Key Research and Development Program of Shaanxi under Grant No.2020ZDLGY08-04;the Key Technologies R&D Program of He’nan Province under Grant No.212102210084;the Innovation Scientists and Technicians Troop Construction Projects of Henan Province.

摘　　要：As an emerging joint learning model,federated learning is a promising way to combine model parameters of different users for training and inference without collecting users’original data.However,a practical and efficient solution has not been established in previous work due to the absence of efficient matrix computation and cryptography schemes in the privacy-preserving federated learning model,especially in partially homomorphic cryptosystems.In this paper,we propose a Practical and Efficient Privacy-preserving Federated Learning(PEPFL)framework.First,we present a lifted distributed ElGamal cryptosystem for federated learning,which can solve the multi-key problem in federated learning.Secondly,we develop a Practical Partially Single Instruction Multiple Data(PSIMD)parallelism scheme that can encode a plaintext matrix into single plaintext for encryption,improving the encryption efficiency and reducing the communication cost in partially homomorphic cryptosystem.In addition,based on the Convolutional Neural Network(CNN)and the designed cryptosystem,a novel privacy-preserving federated learning framework is designed by using Momentum Gradient Descent(MGD).Finally,we evaluate the security and performance of PEPFL.The experiment results demonstrate that the scheme is practicable,effective,and secure with low communication and computation costs.

关 键 词：Federated learning Partially single instruction multiple data Momentum gradient descent ELGAMAL Multi-key Homomorphic encryption 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]