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
  • [21] Learning Efficiency Maximization for Wireless Federated Learning With Heterogeneous Data and Clients
    Ouyang J.
    Liu Y.
    IEEE Transactions on Cognitive Communications and Networking, 2024, 10 (06): : 1 - 1
  • [22] LEARN: Selecting Samples Without Training Verification for Communication-Efficient Vertical Federated Learning
    Liu, Tong
    Lyu, Feng
    Ma, Jun
    Deng, Yongheng
    Chen, Jiayin
    Tan, Qilong
    Zhang, Yaoxue
    IEEE CONFERENCE ON GLOBAL COMMUNICATIONS, GLOBECOM, 2023, : 1217 - 1222
  • [23] Robust quantum federated learning with noise
    Chen, Liangjun
    Yan, Lili
    Zhang, Shibin
    PHYSICA SCRIPTA, 2024, 99 (07)
  • [24] Regulating Workers in Federated Learning by Yardstick Competition
    Sarikaya, Yunus
    Ercetin, Ozgur
    PROCEEDINGS OF THE 13TH EAI INTERNATIONAL CONFERENCE ON PERFORMANCE EVALUATION METHODOLOGIES AND TOOLS ( VALUETOOLS 2020), 2020, : 150 - 155
  • [25] How to Prevent the Poor Performance Clients for Personalized Federated Learning?
    Qu, Zhe
    Li, Xingyu
    Han, Xiao
    Duan, Rui
    Shen, Chengchao
    Chen, Lixing
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 12167 - 12176
  • [26] Fed-SIc: Selecting Important Clients for Federated Learning
    Lim, Hyun Woo
    Tanjung, Sean Yonathan
    Iwan, Ignatius
    Yahya, Bernardo Nugroho
    Lee, Seok-Lyong
    2023 31ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU, 2023,
  • [27] Ferrari: A Personalized Federated Learning Framework for Heterogeneous Edge Clients
    Yao, Zhiwei
    Liu, Jianchun
    Xu, Hongli
    Wang, Lun
    Qian, Chen
    Liao, Yunming
    IEEE TRANSACTIONS ON MOBILE COMPUTING, 2024, 23 (10) : 10031 - 10045
  • [28] ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients
    Ilhan, Fatih
    Su, Gong
    Liu, Ling
    2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 24532 - 24541
  • [29] Federated learning secure model: A framework for malicious clients detection
    Kolasa, Dominik
    Pilch, Kinga
    Mazurczyk, Wojciech
    SOFTWAREX, 2024, 27
  • [30] Exploration and Exploitation in Federated Learning to Exclude Clients with Poisoned Data
    Tabatabai, Shadha
    Mohammed, Ihab
    Qolomany, Basheer
    Albaseer, Abdullatif
    Ahmad, Kashif
    Abdallah, Mohamed
    Al-Fuqaha, Ala
    2022 INTERNATIONAL WIRELESS COMMUNICATIONS AND MOBILE COMPUTING, IWCMC, 2022, : 407 - 412