Local Model Privacy-Preserving Study for Federated Learning

被引：0
作者：
Pan, Kaiyun [1 ]
He, Daojing [1 ]
Xu, Chuan [2 ]
机构：
[1] East China Normal Univ, Software Engn Inst, Shanghai, Peoples R China
[2] Inria Sophia Antipolis, Valbonne, France
来源：
SECURITY AND PRIVACY IN COMMUNICATION NETWORKS, SECURECOMM 2021, PT I | 2021年 / 398卷
基金：
国家重点研发计划; 中国国家自然科学基金;
关键词：
Federated learning; Privacy-preserving; Distributed optimization; Differential privacy; OPTIMIZATION; COORDINATION;
D O I：
10.1007/978-3-030-90019-9_15
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In federated learning framework, data are kept locally by clients, which provides naturally a certain level of privacy. However, we show in this paper that a curious onlooker can still infer some sensitive information of clients by looking at the exchanged messages. More precisely, for the linear regression task, the onlooker can decode the exact local model of each client in a constant number of rounds under both cross-device and cross-silo federated learning settings. We improve one of the learning algorithms and experimentally show that it makes the onlooker harder to decode the local model of clients.
引用
收藏
页码：287 / 307
页数：21
相关论文
共 50 条
  • [31] In-Network Aggregation for Privacy-Preserving Federated Learning
    Chen, Fahao
    Li, Peng
    Miyazaki, Toshiaki
    2021 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES FOR DISASTER MANAGEMENT (ICT-DM), 2021, : 49 - 56
  • [32] Privacy-preserving federated learning compatible with robust aggregators
    Alebouyeh, Zeinab
    Bidgoly, Amir Jalaly
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2025, 143
  • [33] Privacy-Preserving Federated Edge Learning: Modeling and Optimization
    Liu, Tianyu
    Di, Boya
    Song, Lingyang
    IEEE COMMUNICATIONS LETTERS, 2022, 26 (07) : 1489 - 1493
  • [34] Privacy-preserving federated learning based on noise addition
    Wu, Xianlin
    Chen, Yuwen
    Yu, Haiyang
    Yang, Zhen
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 267
  • [35] Privacy-preserving federated learning with non-transfer learning
    Xu M.
    Li X.
    Xi'an Dianzi Keji Daxue Xuebao/Journal of Xidian University, 2023, 50 (04): : 89 - 99
  • [36] Empowering federated learning techniques for privacy-preserving PV
    Michalakopoulos, Vasilis
    Sarantinopoulos, Efstathios
    Sarmas, Elissaios
    Marinakis, Vangelis
    ENERGY REPORTS, 2024, 12 : 2244 - 2256
  • [37] A Novel Approach for Differential Privacy-Preserving Federated Learning
    Elgabli, Anis
    Mesbah, Wessam
    IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY, 2025, 6 : 466 - 476
  • [38] Staged Noise Perturbation for Privacy-Preserving Federated Learning
    Li, Zhe
    Chen, Honglong
    Gao, Yudong
    Ni, Zhichen
    Xue, Huansheng
    Shao, Huajie
    IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING, 2024, 9 (06): : 936 - 947
  • [39] Privacy-Preserving Efficient Federated-Learning Model Debugging
    Li, Anran
    Zhang, Lan
    Wang, Junhao
    Han, Feng
    Li, Xiang-Yang
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2022, 33 (10) : 2291 - 2303
  • [40] Privacy-preserving clustering federated learning for non-IID data
    Luo, Guixun
    Chen, Naiyue
    He, Jiahuan
    Jin, Bingwei
    Zhang, Zhiyuan
    Li, Yidong
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2024, 154 : 384 - 395
12345