Trustworthy decentralized collaborative learning for edge intelligence: A survey

被引:2
|
作者
Yu, Dongxiao [1 ]
Xie, Zhenzhen [1 ]
Yuan, Yuan [2 ]
Chen, Shuzhen [1 ]
Qiao, Jing [1 ]
Wang, Yangyang [1 ]
Yu, Yong [3 ]
Zou, Yifei [1 ]
Zhang, Xiao [1 ]
机构
[1] Shandong Univ, Sch Comp Sci & Technol, Qingdao 266237, Peoples R China
[2] Shandong Univ, Ctr Artificial Intelligence Res C FAIR, Sch Software & Joint SDU NTU, Jinan 250101, Peoples R China
[3] Shaanxi Normal Univ, Sch Comp Sci, Xian 710062, Peoples R China
来源
HIGH-CONFIDENCE COMPUTING | 2023年 / 3卷 / 03期
关键词
Trustworthy machine learning; Decentralized collaborative learning; Security; Robustness; Privacy;
D O I
10.1016/j.hcc.2023.100150
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Edge intelligence is an emerging technology that enables artificial intelligence on connected systems and devices in close proximity to the data sources. decentralized collaborative learning (DCL) is a novel edge intelligence technique that allows distributed clients to cooperatively train a global learning model without revealing their data. DCL has a wide range of applications in various domains, such as smart city and autonomous driving. However, DCL faces significant challenges in ensuring its trustworthiness, as data isolation and privacy issues make DCL systems vulnerable to adversarial attacks that aim to breach system confidentiality, undermine learning reliability or violate data privacy. Therefore, it is crucial to design DCL in a trustworthy manner, with a focus on security, robustness, and privacy. In this survey, we present a comprehensive review of existing efforts for designing trustworthy DCL systems from the three key aformentioned aspects: security, robustness, and privacy. We analyze the threats that affect the trustworthiness of DCL across different scenarios and assess specific technical solutions for achieving each aspect of trustworthy DCL (TDCL). Finally, we highlight open challenges and future directions for advancing TDCL research and practice. (c) 2023 The Author(s). Published by Elsevier B.V. on behalf of Shandong University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Survey of edge–edge collaborative training for edge intelligence
    Wang R.
    Wang Y.
    Yin P.
    Qi J.-P.
    Sun Y.-T.
    Li Q.
    Zhang Y.-D.
    Zhang M.-K.
    Gongcheng Kexue Xuebao/Chinese Journal of Engineering, 2023, 45 (08): : 1400 - 1416
  • [2] Survey of Collaborative Inference for Edge Intelligence
    Wang R.
    Qi J.
    Chen L.
    Yang L.
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2023, 60 (02): : 398 - 414
  • [3] A Survey on Collaborative DNN Inference for Edge Intelligence
    Wei-Qing Ren
    Yu-Ben Qu
    Chao Dong
    Yu-Qian Jing
    Hao Sun
    Qi-Hui Wu
    Song Guo
    Machine Intelligence Research, 2023, 20 : 370 - 395
  • [4] A Survey on Collaborative DNN Inference for Edge Intelligence
    Ren, Wei-Qing
    Qu, Yu-Ben
    Dong, Chao
    Jing, Yu-Qian
    Sun, Hao
    Wu, Qi-Hui
    Guo, Song
    MACHINE INTELLIGENCE RESEARCH, 2023, 20 (03) : 370 - 395
  • [5] Collaborative Trustworthy Framework for Edge Computing
    He Xinfeng
    Tian Junfeng
    Lou Jian
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2022, 44 (12) : 4256 - 4264
  • [6] Blockchain-Enabled Decentralized Edge Intelligence for Trustworthy 6G Consumer Electronics
    Wang, Xin
    Shankar, Achyut
    Li, Keqin
    Parameshachari, B. D.
    Lv, Jianhui
    IEEE TRANSACTIONS ON CONSUMER ELECTRONICS, 2024, 70 (01) : 1214 - 1225
  • [7] A Review on Edge Intelligence based Collaborative Learning Approaches
    Welagedara, Lahiru
    Harischandra, Janani
    Jayawardene, Nuwan
    2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2021, : 572 - 577
  • [8] Blockchain-based Collaborative Edge Intelligence for Trustworthy and Real-Time Video Surveillance
    Zhang, Mingjin
    Cao, Jiannong
    Sahni, Yuvraj
    Chen, Qianyi
    Jiang, Shan
    Yang, Lei
    IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2023, 19 (02) : 1623 - 1633
  • [9] Trustworthy machine learning and artificial intelligence
    Varshney, Kush R.
    XRDS: Crossroads, 2019, 25 (03): : 26 - 29
  • [10] Sustainable and Trustworthy Edge Machine Learning
    Brandic, Ivona
    IEEE INTERNET COMPUTING, 2021, 25 (05) : 5 - 9