网络与信息安全学报 ›› 2021, Vol. 7 ›› Issue (5): 77-92.doi: 10.11959/j.issn.2096-109x.2021056

所属专题: 联邦学习

• 专栏Ⅱ:机器学习及安全应用 • 上一篇    下一篇

联邦学习研究综述

周传鑫, 孙奕, 汪德刚, 葛桦玮   

  1. 信息工程大学,河南 郑州 450001
  • 修回日期:2020-10-10 出版日期:2021-10-15 发布日期:2021-10-01
  • 作者简介:周传鑫(1997− ),男,安徽蚌埠人,信息工程大学硕士生,主要研究方向为数据安全交换、机器学习和隐私保护
    孙奕(1979− ),女,河南郑州人,博士,信息工程大学副教授,主要研究方向为网络与信息安全、数据安全交换
    汪德刚(1996− ),男,陕西安康人,信息工程大学硕士生,主要研究方向为数据安全交换、恶意流量检测
    葛桦玮(1998− ),男,浙江临海人,主要研究方向为数据安全交换
  • 基金资助:
    国家自然科学基金(61702550)

Survey of federated learning research

Chuanxin ZHOU, Yi SUN, Degang WANG, Huawei GE   

  1. Information Engineering University, Zhenghzou 450001, China
  • Revised:2020-10-10 Online:2021-10-15 Published:2021-10-01
  • Supported by:
    The National Natural Science Foundation of China(61702550)

摘要:

联邦学习由于能够在多方数据源聚合的场景下协同训练全局最优模型,近年来迅速成为安全机器学习领域的研究热点。首先,归纳了联邦学习定义、算法原理和分类;接着,深入分析了其面临的主要威胁与挑战;然后,重点对通信效率、隐私安全、信任与激励机制3个方向的典型研究方案对比分析,指出其优缺点;最后,结合边缘计算、区块链、5G等新兴技术对联邦学习的应用前景及研究热点进行展望。

关键词: 联邦学习, 隐私保护, 区块链, 边缘计算

Abstract:

Federated learning has rapidly become a research hotspot in the field of security machine learning in recent years because it can train the global optimal model collaboratively without the need for multiple data source aggregation.Firstly, the federated learning framework, algorithm principle and classification were summarized.Then, the main threats and challenges it faced, were analysed indepth the comparative analysis of typical research programs in the three directions of communication efficiency, privacy and security, trust and incentive mechanism was focused on, and their advantages and disadvantages were pointed out.Finally, Combined with application of edge computing, blockchain, 5G and other emerging technologies to federated learning, its future development prospects and research hotspots was prospected.

Key words: federated learning, privacy protection, blockchain, edge of computing

中图分类号: 

No Suggested Reading articles found!