Privacy-Preserving Collaborative Learning With Linear Communication Complexity

被引:1
作者
Lu, Xingyu [1 ]
Sami, Hasin Us [1 ]
Guler, Basak [1 ]
机构
[1] Univ Calif Riverside, Dept Elect & Comp Engn, Riverside, CA 92521 USA
关键词
Training; Computational modeling; Cryptography; Privacy; Information theory; Resilience; Protocols; Coded computing; distributed training; collaborative machine learning; information-theoretic privacy; COMPUTATION;
D O I
10.1109/TIT.2023.3345270
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Collaborative machine learning enables privacy-preserving training of machine learning models without collecting sensitive client data. Despite recent breakthroughs, communication bottleneck is still a major challenge against its scalability to larger networks. To address this challenge, in this work we propose PICO, the first collaborative learning framework with linear communication complexity, significantly improving over the quadratic state-of-the-art, under formal information-theoretic privacy guarantees. Theoretical analysis demonstrates that PICO slashes the communication cost while achieving equal computational complexity, adversary resilience, robustness to client dropouts, and model accuracy to the state-of-the-art. Extensive experiments demonstrate up to 91x reduction in the communication overhead, and up to 8x speed-up in the wall-clock training time compared to the state-of-the-art. As such, PICO addresses a key technical challenge in multi-party collaborative learning, paving the way for future large-scale privacy-preserving learning frameworks.
引用
收藏
页码:5857 / 5887
页数:31
相关论文
共 50 条
[41]   Privacy-preserving SVANETs Privacy-preserving Simple Vehicular Ad-hoc Networks [J].
Hajny, Jan ;
Malina, Lukas ;
Martinasek, Zdenek ;
Zeman, Vaclav .
PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON SECURITY AND CRYPTOGRAPHY (SECRYPT 2013), 2013, :267-274
[42]   PFLF: Privacy-Preserving Federated Learning Framework for Edge Computing [J].
Zhou, Hao ;
Yang, Geng ;
Dai, Hua ;
Liu, Guoxiu .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 :1905-1918
[43]   CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learning [J].
Wang, Jianhua ;
Chang, Xiaolin ;
Misic, Jelena ;
Misic, Vojislav B. ;
Li, Lin ;
Yao, Yingying .
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2025, 22 (01) :198-208
[44]   Privacy-Preserving Collective Learning With Homomorphic Encryption [J].
Paul, Jestine ;
Annamalai, Meenatchi Sundaram Muthu Selva ;
Ming, William ;
Al Badawi, Ahmad ;
Veeravalli, Bharadwaj ;
Aung, Khin Mi Mi .
IEEE ACCESS, 2021, 9 :132084-132096
[45]   Anonymous and Efficient Authentication Scheme for Privacy-Preserving Distributed Learning [J].
Jiang, Yili ;
Zhang, Kuan ;
Qian, Yi ;
Zhou, Liang .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2022, 17 :2227-2240
[46]   Privacy-Preserving Federated Learning via Functional Encryption, Revisited [J].
Chang, Yansong ;
Zhang, Kai ;
Gong, Junqing ;
Qian, Haifeng .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 :1855-1869
[47]   Efficient Verifiable Protocol for Privacy-Preserving Aggregation in Federated Learning [J].
Eltaras, Tamer ;
Sabry, Farida ;
Labda, Wadha ;
Alzoubi, Khawla ;
Malluhi, Qutaibah .
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 :2977-2990
[48]   Privacy-Preserving Multilayer Community Detection via Federated Learning [J].
Ma, Shi-Yao ;
Xu, Xiao-Ke ;
Xiao, Jing .
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, 2024,
[49]   Incentive Compatible Privacy-Preserving Data Analysis [J].
Kantarcioglu, Murat ;
Jiang, Wei .
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2013, 25 (06) :1323-1335
[50]   Privacy-Preserving Machine Learning Training in IoT Aggregation Scenarios [J].
Zhu, Liehuang ;
Tang, Xiangyun ;
Shen, Meng ;
Gao, Feng ;
Zhang, Jie ;
Du, Xiaojiang .
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (15) :12106-12118