PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks

被引:64
|
作者
Mandal, Kalikinkar [1 ]
Gong, Guang [1 ]
机构
[1] Univ Waterloo, Waterloo, ON, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Privacy-preserving computation; Predictive analysis; Federated learning; Machine learning;
D O I
10.1145/3338466.3358926
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Federated Learning (FL) enables a large number of users to jointly learn a shared machine learning (ML) model, coordinated by a centralized server, where the data is distributed across multiple devices. This approach enables the server or users to train and learn an ML model using gradient descent, while keeping all the training data on users' devices. We consider training an ML model over a mobile network where user dropout is a common phenomenon. Although federated learning was aimed at reducing data privacy risks, the ML model privacy has not received much attention. In this work, we present PrivFL, a privacy-preserving system for training (predictive) linear and logistic regression models and oblivious predictions in the federated setting, while guaranteeing data and model privacy as well as ensuring robustness to users dropping out in the network. We design two privacy-preserving protocols for training linear and logistic regression models based on an additive homomorphic encryption (HE) scheme and an aggregation protocol. Exploiting the training algorithm of federated learning, at the core of our training protocols is a secure multiparty global gradient computation on alive users' data. We analyze the security of our training protocols against semi-honest adversaries. As long as the aggregation protocol is secure under the aggregation privacy game and the additive HE scheme is semantically secure, PrivFL guarantees the users' data privacy against the server, and the server's regression model privacy against the users. We demonstrate the performance of PrivFL on real-world datasets and show its applicability in the federated learning system.
引用
收藏
页码:57 / 68
页数:12
相关论文
共 50 条
  • [1] Privacy-preserving high-dimensional data publishing for classification
    Wang, Rong
    Zhu, Yan
    Chang, Chin-Chen
    Peng, Qiang
    COMPUTERS & SECURITY, 2020, 93
  • [2] Fusion: Privacy-preserving Distributed Protocol for High-Dimensional Data Mashup
    Dagher, Gaby G.
    Iqbal, Farkhund
    Arafati, Mahtab
    Fung, Benjamin C. M.
    2015 IEEE 21ST INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2015, : 760 - 769
  • [3] PHRkNN: Efficient and Privacy-Preserving Reverse kNN Query Over High-Dimensional Data in Cloud
    Zheng, Yandong
    Zhu, Hui
    Lu, Rongxing
    Guan, Yunguo
    Zhang, Songnian
    Wang, Fengwei
    Shao, Jun
    Li, Hui
    IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING, 2024, 21 (04) : 1831 - 1844
  • [4] Privacy-Preserving Federated Learning for Data Heterogeneity in 6G Mobile Networks
    Zhang, Chuan
    Ren, Xuhao
    Zhang, Weiting
    Yuan, Yanli
    Xiong, Zehui
    Li, Chunhai
    Zhu, Liehuang
    IEEE NETWORK, 2025, 39 (02): : 134 - 141
  • [5] Privacy-Preserving Federated Data Sharing
    Fioretto, Ferdinando
    Van Hentenryck, Pascal
    AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 638 - 646
  • [6] Fedlabx: a practical and privacy-preserving framework for federated learning
    Yan, Yuping
    Kamel, Mohammed B. M.
    Zoltay, Marcell
    Gal, Marcell
    Hollos, Roland
    Jin, Yaochu
    Peter, Ligeti
    Tenyi, Akos
    COMPLEX & INTELLIGENT SYSTEMS, 2024, 10 (01) : 677 - 690
  • [7] Privacy-preserving and homogeneity-pursuit integrative analysis for high-dimensional censored data
    Ye, Xin
    He, Baihua
    Liu, Yanyan
    Ma, Shuangge
    STATISTICAL PAPERS, 2024, 65 (04) : 2165 - 2190
  • [8] A divide-and-conquer approach to privacy-preserving high-dimensional big data release
    Wang, Rong
    Liang, Junchuan
    Wang, Siyu
    Chang, Chin-Chen
    JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2024, 83
  • [9] Privacy-Preserving Federated Depression Detection From Multisource Mobile Health Data
    Xu, Xiaohang
    Peng, Hao
    Bhuiyan, Md Zakirul Alam
    Hao, Zhifeng
    Liu, Lianzhong
    Sun, Lichao
    He, Lifang
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2022, 18 (07) : 4788 - 4797
  • [10] PAD: Privacy-Preserving Data Dissemination in Mobile Social Networks
    Zhong, Peixiang
    Lu, Rongxing
    2014 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS (ICCS), 2014, : 243 - 247