所属单位：计算机科学与工程学院

发表刊物：IEEE Internet of Things Journal

项目来源：省、市、自治区科技项目

关键字：Federated Learning, Privacy-Preservation, Secure Multi-party Computing, FedAVG Algorithm.

摘要：Federated learning is a promising new technology in the field of IoT intelligence. However, exchanging modelrelated data in federated learning may leak the sensitive information of participants. To address this problem, we propose a novel privacy-preserving FL framework based on an innovative chained secure multi-party computing technique, named ChainPPFL. Our scheme mainly leverages two mechanisms: SingleMasking mechanism which protects information exchanged between participants; Chained-Communication mechanism which enables masked information to be transferred between participants with a serial chain frame. We conduct extensive simulation-based experiments using two public datasets (MNIST and CIFAR-100) by comparing both training accuracy and leakdefence with other state-of-the-art schemes. We set two data sample distributions (IID and Non-IID) and three training models (CNN, MLP and L-BFGS) in our experiments. The experimental results demonstrate that the Chain-PPFL scheme can achieve a practical privacy-preservation (equivalent to differential privacy with  approaching zero) for federated learning with some cost of communication and without impairing the accuracy and convergence speed of the training model.

合写作者：Yipeng Zhou,Alireza Jolfaei,俞东进,徐高潮,Xi Zheng

第一作者：李勇

论文类型：期刊论文

卷号：8

期号：8

页面范围：1

字数：1

ISSN号：2327-4662

是否译文：否

发表时间：2021-04-15