High-accuracy low-cost privacy-preserving federated learning in IoT systems via adaptive perturbation

被引:5
|
作者
Liu, Tian [1 ,2 ]
Hu, Xueyang [1 ]
Xu, Hairuo [1 ]
Shu, Tao [1 ]
Nguyen, Diep N. [3 ]
机构
[1] Auburn Univ, Dept Comp Sci & Software Engn, Auburn, AL 36849 USA
[2] Zhejiang Lab, Hangzhou, Peoples R China
[3] Univ Technol Sydney, Sch Elect & Data Engn, Sydney, NSW, Australia
基金
美国国家科学基金会;
关键词
Federated learning; Privacy-preserving; IoT; Convergence performance; Information leakage; Local privacy;
D O I
10.1016/j.jisa.2022.103309
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid development of the Internet of Things (IoT), federated learning (FL) has been widely used to obtain insights from collected data while preserving data privacy. Differential privacy (DP) is an additive noise scheme that has been widely studied as a privacy-preserving approach on FL. However, privacy protection under DP usually comes at the cost of model accuracy for the underlying FL process. In this paper, we propose a novel low-cost (for both communication and computational overhead) adaptive noise perturbation/masking scheme to protect FL clients' privacy without degrading the global model accuracy. In particular, we set the magnitude of the additive noise to adaptively change with the magnitude of the local model updates. Then, a direction-based filtering scheme is used to accelerate the convergence of the FL model. A maximum tolerable noise bound for local clients is derived using the central limit theorem (CLT). The designed noise maximizes privacy protection for clients while preserving the accuracy and convergence rate of the FL model , as a result of the noise cancelling out and forming a more concentrated distribution after the aggregation operation on the server. We theoretically prove that FL with the proposed noise perturbation scheme retains the same accuracy and convergence rate (O(1/T) for convex loss functions and O(1/root T) for non-convex loss functions) as that of non-private FL with SGD. We also evaluate the performance of the proposed scheme in terms of convergence behavior, computational efficiency, and privacy protection against state-of-the-art privacy inference attacks on real-world datasets. Experimental results show that FL with our proposed perturbation scheme outperforms DP in the accuracy and convergence rate of the FL model in both client dropout and non -client dropout scenarios. Compared with DP, our proposed scheme does not incur additional computational and communication overhead. Our approach provides DP-comparable or better effectiveness in defending against privacy attacks under the same global model accuracy.
引用
收藏
页数:15
相关论文
共 50 条
  • [41] Privacy-Preserving Cross-Silo Federated Learning Atop Blockchain for IoT
    Li, Huilin
    Sun, Yu
    Yu, Yong
    Li, Dawei
    Guan, Zhenyu
    Liu, Jianwei
    IEEE INTERNET OF THINGS JOURNAL, 2023, 10 (24) : 21176 - 21186
  • [42] VFL: A Verifiable Federated Learning With Privacy-Preserving for Big Data in Industrial IoT
    Fu, Anmin
    Zhang, Xianglong
    Xiong, Naixue
    Gao, Yansong
    Wang, Huaqun
    Zhang, Jing
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (05) : 3316 - 3326
  • [43] FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation
    Gu, Hanlin
    Luo, Jiahuan
    Kang, Yan
    Fan, Lixin
    Yang, Qiang
    PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 3759 - 3767
  • [44] Adaptive Privacy-Preserving Federated Learning for Fault Diagnosis in Internet of Ships
    Zhang, Zehui
    Guan, Cong
    Chen, Hui
    Yang, Xiangguo
    Gong, Wenfeng
    Yang, Ansheng
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (09) : 6844 - 6854
  • [45] Privacy-Preserving Continuous Authentication for Mobile and IoT Systems Using Warmup-Based Federated Learning
    Wazzeh, Mohamad
    Ould-Slimane, Hakima
    Talhi, Chamseddine
    Mourad, Azzam
    Guizani, Mohsen
    IEEE NETWORK, 2023, 37 (03): : 224 - 230
  • [46] FedGRU: Privacy-preserving Traffic Flow Prediction via Federated Learning
    Liu, Yi
    Zhang, Shuyu
    Zhang, Chenhan
    Yu, James J. Q.
    2020 IEEE 23RD INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), 2020,
  • [47] Lightweight and Dynamic Privacy-Preserving Federated Learning via Functional Encryption
    Yu, Boan
    Zhao, Jun
    Zhang, Kai
    Gong, Junqing
    Qian, Haifeng
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2025, 20 : 2496 - 2508
  • [48] CryptoFE: Practical and Privacy-Preserving Federated Learning via Functional Encryption
    Qian, Xinyuan
    Li, Hongwei
    Hao, Meng
    Yuan, Shuai
    Zhang, Xilin
    Guo, Song
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 2999 - 3004
  • [49] PILE: Robust Privacy-Preserving Federated Learning Via Verifiable Perturbations
    Tang, Xiangyun
    Shen, Meng
    Li, Qi
    Zhu, Liehuang
    Xue, Tengfei
    Qu, Qiang
    IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2023, 20 (06) : 5005 - 5023
  • [50] FedMDO: Privacy-Preserving Federated Learning via Mixup Differential Objective
    You, Xianyao
    Liu, Caiyun
    Li, Jun
    Sun, Yan
    Liu, Ximeng
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (10) : 10449 - 10463