Regulating Clients' Noise Adding in Federated Learning without Verification

被引:0
|
作者
Hong, Shu [1 ]
Duan, Lingjie [1 ]
机构
[1] Singapore Univ Technol & Design, Singapore, Singapore
关键词
D O I
10.1109/ICC45041.2023.10279141
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
In federated learning (FL), clients cooperatively train a global model without revealing their raw data but gradients or parameters, while the local information can still be disclosed from local outputs transmitted to the parameter server. With such privacy concerns, a client may overly add artificial noise to his local updates to compromise the global model training, and we prove the selfish noise adding leads to an infinite price of anarchy (PoA). This paper proposes a novel pricing mechanism to regulate privacy-sensitive clients without verifying their parameter updates, unlike existing privacy mechanisms that assume the server's full knowledge of added noise. Without knowing the ground truth, our mechanism reaches the social optimum to best balance the global training error and privacy loss, according to the difference between a client's updated parameter and all clients' average parameter. We also improve the FL convergence bound by refining the aggregation rule at the server to account for different clients' noise variances. Moreover, we extend our pricing scheme to fit incomplete information of clients' privacy sensitivities, ensuring their truthful type reporting and the system's ex-ante budget balance. Simulations show that our pricing scheme greatly improves the system performance especially when clients have diverse privacy sensitivities.
引用
收藏
页码:1244 / 1249
页数:6
相关论文
共 50 条
  • [41] FedCime: An Efficient Federated Learning Approach For Clients in Mobile Edge Computing
    Agbaje, Paul
    Anjum, Afia
    Talukder, Zahidur
    Islam, Mohammad
    Nwafor, Ebelechukwu
    Olufowobi, Habeeb
    2023 IEEE INTERNATIONAL CONFERENCE ON EDGE COMPUTING AND COMMUNICATIONS, EDGE, 2023, : 215 - 220
  • [42] Asynchronous Semi-Decentralized Federated Edge Learning for Heterogeneous Clients
    Sun, Yuchang
    Shao, Jiawei
    Mao, Yuyi
    Zhang, Jun
    IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC 2022), 2022, : 5196 - 5201
  • [43] FedNaWi: Selecting the Befitting Clients for Robust Federated Learning in IoT Applications
    Zhu, Ran
    Yang, Mingkun
    Yang, Jie
    Wang, Qing
    2023 20TH ANNUAL IEEE INTERNATIONAL CONFERENCE ON SENSING, COMMUNICATION, AND NETWORKING, SECON, 2023,
  • [44] On the Convergence of Hybrid Federated Learning with Server-Clients Collaborative Training
    Yang, Kun
    Shen, Cong
    2022 56TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS), 2022, : 252 - 257
  • [45] DDoS Attacks in Communication: Analysis and Mitigation of Unreliable Clients in Federated Learning
    Sanon, Sogo Pierre
    Reddy, Rekha
    Lipps, Christoph
    Schotten, Hans Dieter
    2024 IEEE 21ST CONSUMER COMMUNICATIONS & NETWORKING CONFERENCE, CCNC, 2024, : 986 - 989
  • [46] A systematic review of federated learning from clients’ perspective: challenges and solutions
    Yashothara Shanmugarasa
    Hye-young Paik
    Salil S. Kanhere
    Liming Zhu
    Artificial Intelligence Review, 2023, 56 : 1773 - 1827
  • [47] Multi-center federated learning: clients clustering for better personalization
    Long, Guodong
    Xie, Ming
    Shen, Tao
    Zhou, Tianyi
    Wang, Xianzhi
    Jiang, Jing
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2023, 26 (01): : 481 - 500
  • [48] Federated Learning for Clients' Data Privacy Assurance in Food Service Industry
    Taheri Gorji, Hamed
    Saeedi, Mahdi
    Mushtaq, Erum
    Zadeh, Hossein Kashani
    Husarik, Kaylee
    Shahabi, Seyed Mojtaba
    Qin, Jianwei
    Chan, Diane E.
    Baek, Insuck
    Kim, Moon S.
    Akhbardeh, Alireza
    Sokolov, Stanislav
    Avestimehr, Salman
    Mackinnon, Nicholas
    Vasefi, Fartash
    Tavakolian, Kouhyar
    APPLIED SCIENCES-BASEL, 2023, 13 (16):
  • [49] Accelerating Federated Learning via Sequential Training of Grouped Heterogeneous Clients
    Silvi, Andrea
    Rizzardi, Andrea
    Caldarola, Debora
    Caputo, Barbara
    Ciccone, Marco
    IEEE ACCESS, 2024, 12 : 57043 - 57058
  • [50] Adaptive Clustered Federated Learning for Clients with Time-Varying Interests
    Wang, Ne
    Zhou, Ruiting
    Su, Lina
    Fang, Guang
    Li, Zongpeng
    2022 IEEE/ACM 30TH INTERNATIONAL SYMPOSIUM ON QUALITY OF SERVICE (IWQOS), 2022,