Secure Gradient Aggregation for Wireless Multi-Server Federated Learning

doi:10.1109/ISIT54713.2023.10206522

	Secure Gradient Aggregation for Wireless Multi-Server Federated Learning
	Zhenhao Huang1 ; Songze Li 2; Kai Liang1 ; Youlong Wu1
	2023-06-25
会议录名称	2023 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT)
ISSN	2157-8095
卷号	2023-June
页码	2404-2409
发表状态	已发表
DOI	10.1109/ISIT54713.2023.10206522
摘要	In this paper, we investigate the secure gradient aggregation problem for K-server wireless Federated learning (FL) systems. We propose a coded aggregation scheme such that any set of up to T colluding servers cannot infer any information about the local updates, including the aggregation value. In our scheme, each user encodes its local update to K confidential messages using Lagrange Coding, and then sends one confidential message to each server using an artificial noise alignment approach. In the downlink, each server delivers the summation of the confidential messages, by which every user can recover the aggregation of local updates. For the proposed scheme, we characterize the uplink and downlink communication latency, and show that the communication latency monotonically decreases with the total number of servers K while increasing with the number of colluding servers T. © 2023 IEEE.
会议录编者/会议主办者	Entropy ; Google ; Huawei ; Mediatek ; NSF ; Qualcomm
关键词	Wireless communication Wireless sensor networks Federated learning Downlink Encoding Servers Communication system security
会议名称	2023 IEEE International Symposium on Information Theory, ISIT 2023
会议地点	Taipei, Taiwan
会议日期	25-30 June 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20233814753519
原始文献类型	Conference article (CA)
来源库	IEEE
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/333417
专题	信息科学与技术学院信息科学与技术学院_PI研究组_吴幼龙组信息科学与技术学院_博士生
作者单位	1.School of Information Science and Technology, ShanghaiTech University, China 2.IoT Thrust, The Hong Kong University of Science and Technology, Guangzhou, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Zhenhao Huang,Songze Li,Kai Liang,et al. Secure Gradient Aggregation for Wireless Multi-Server Federated Learning[C]//Entropy, Google, Huawei, Mediatek, NSF, Qualcomm:Institute of Electrical and Electronics Engineers Inc.,2023:2404-2409.