| 注册
首页|期刊导航|计算机工程与应用|联邦学习中的攻击手段与防御机制研究综述

联邦学习中的攻击手段与防御机制研究综述

张世文 陈双 梁伟 李仁发

计算机工程与应用2024,Vol.60Issue(5):1-16,16.
计算机工程与应用2024,Vol.60Issue(5):1-16,16.DOI:10.3778/j.issn.1002-8331.2306-0243

联邦学习中的攻击手段与防御机制研究综述

Survey on Attack Methods and Defense Mechanisms in Federated Learning

张世文 1陈双 1梁伟 1李仁发2

作者信息

  • 1. 湖南科技大学 计算机科学与工程学院,湖南 湘潭 411201
  • 2. 湖南大学 信息科学与工程学院,长沙 410082
  • 折叠

摘要

Abstract

The attack and defense techniques of federated learning are the core issue of federated learning system security.The attack and defense techniques of federated learning can significantly reduce the risk of being attacked and greatly enhance the security of federated learning systems.Deeply understanding the attack and defense techniques of federated learning can advance research in the field and achieve its widespread application of federated learning.Therefore,it is of great significance to study the attack and defense techniques of federated learning.Firstly,this paper briefly introduces the concept,basic workflow,types,and potential existing security issues of federated learning.Subsequently,the paper intro-duces the attacks that the federated learning system may encounter,and relevant research is summarized during the intro-duction.Then,starting from whether the federated learning system has targeted defense measures,the defense measures are divided into two categories:universal defense measures and targeted defense measures,and targeted summary are made.Finally,it reviews and analyzes the future research directions for the security of federated learning,providing refer-ence for relevant researchers in their research work on the security of federated learning.

关键词

联邦学习/攻击手段/防御措施/隐私保护

Key words

federated learning/attack method/defense mechanism/privacy protection

分类

信息技术与安全科学

引用本文复制引用

张世文,陈双,梁伟,李仁发..联邦学习中的攻击手段与防御机制研究综述[J].计算机工程与应用,2024,60(5):1-16,16.

基金项目

国家自然科学基金(61702180) (61702180)

湖南省自然科学基金面上项目(2022JJ30267) (2022JJ30267)

福建省自然科学基金(2022J05106) (2022J05106)

湖南省教育厅优秀青年项目(21B0493). (21B0493)

计算机工程与应用

OA北大核心CSTPCD

1002-8331

访问量0
|
下载量0
段落导航相关论文