ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
会议论文

Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise

Fu, Jie; Chen, Zhili*; Han, Xiao
21st IEEE International Conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom)2022DOI: 10.1109/TrustCom56396.2022.00094
1被引6阅读
引用收藏
分享

摘要

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model parameters, such as deep neural network model weights. Recently, differential privacy has been applied to federated learning to protect data privacy, but the noise added may degrade the learning performance much. Typically, in previous work, training parameters were clipped equally and noises were added uniformly. The heterogeneity and convergence of training parameters were simply not considered. In this paper, we propose a differentially private scheme for federated learning with adaptive noise (Adap DP-FL). Specifically, due to the gradient heterogeneity, we conduct adaptive gradient clipping for different clients and different rounds; due to the gradient convergence, we add decreasing noises accordingly. Extensive experiments on real-world datasets demonstrate that our Adap DP-FL outperforms previous methods significantly.

学科与关键词

关键词
information security and privacyfederated learningdifferential privacyadaptive noiseedge compute
相关
加载中…
  • Hierarchical federated learning with global differential privacy
    Long, Youqun; Zhang, Jianhui; Wang, Gaoli*; Fu, JieElectronic Research Archive, 2023, 31(7): 3741-3758.
  • FL2DP: Privacy-Preserving Federated Learning Via Differential Privacy for Artificial IoT
    Gu, Chen; Cui, Xuande; Zhu, Xiaoling; Hu, Donghui*IEEE Transactions on Industrial Informatics, 2023.被引 1
  • Hybrid differential privacy based federated learning for Internet of Things
    Liu, Wenyan; Cheng, Junhong; Wang, Xiaoling; Lu, Xingjian*; Yin, JianweiJOURNAL OF SYSTEMS ARCHITECTURE, 2022, 124: 102418.被引 9
查看全部 →

会议信息

会议名称
21st IEEE International Conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom)
会议日期
2022-12-09 至 2022-12-11
论文集名
2022 IEEE INTERNATIONAL CONFERENCE ON TRUST, SECURITY AND PRIVACY IN COMPUTING AND COMMUNICATIONS, TRUSTCOM
发表日期
2022
起止页码
656-663
DOI
10.1109/TrustCom56396.2022.00094
资助标注
Natural Science Foundation of Shanghai [22ZR1419100]; National Natural Science Foundation of China [62132005]
收录
ISTP

作者

  • F

    Fu, Jie (第一作者)

  • C

    Chen, Zhili (通讯)

查看全部 3 位作者收起作者
  • H

    Han, Xiao

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417