FedPTA: Prior-Based Tensor Approximation for Detecting Malicious Clients in Federated Learning

被引：0
|
作者：
Mu, Xutong [1 ]
Cheng, Ke [1 ,2 ]
Liu, Teng [1 ]
Zhang, Tao [1 ]
Geng, Xueli [3 ]
Shen, Yulong [1 ]
机构：
[1] Xidian University, School of Computer Science and Technology, Shaanxi, Xi'an,710071, China
[2] Xi'an University of Posts and Telecommunications, Shaanxi Key Laboratory of Information Communication Network and Security, Shaanxi, Xi'an,710121, China
[3] Xidian University, School of Artificial Intelligence, Shaanxi, Xi'an,710071, China
来源：
IEEE Transactions on Information Forensics and Security | 2024年 / 19卷
关键词：
Compendex;
D O I：
10.1109/TIFS.2024.3451359
中图分类号：
学科分类号：
摘要：
Federated learning
引用
收藏
页码：9100 / 9114
相关论文
共 50 条
  • [1] Prior-Based Tensor Approximation for Anomaly Detection in Hyperspectral Imagery
    Li, Lu
    Li, Wei
    Qu, Ying
    Zhao, Chunhui
    Tao, Ran
    Du, Qian
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (03) : 1037 - 1050
  • [2] Provably Secure Federated Learning against Malicious Clients
    Cao, Xiaoyu
    Jia, Jinyuan
    Gong, Neil Zhenqiang
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 6885 - 6893
  • [3] FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients
    Zhang, Zaixi
    Cao, Xiaoyu
    Jia, Jinyuan
    Gong, Neil Zhenqiang
    [J]. PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, : 2545 - 2555
  • [4] How to cope with malicious federated learning clients: An unsupervised learning-based approach
    Onsu, Murat Arda
    Kantarci, Burak
    Boukerche, Azzedine
    [J]. COMPUTER NETWORKS, 2023, 234
  • [5] Federated learning secure model: A framework for malicious clients detection
    Kolasa, Dominik
    Pilch, Kinga
    Mazurczyk, Wojciech
    [J]. SOFTWAREX, 2024, 27
  • [6] Long-Short History of Gradients Is All You Need: Detecting Malicious and Unreliable Clients in Federated Learning
    Gupta, Ashish
    Luo, Tie
    Ngo, Mao V.
    Das, Sajal K.
    [J]. COMPUTER SECURITY - ESORICS 2022, PT III, 2022, 13556 : 445 - 465
  • [7] On the Impact of Malicious and Cooperative Clients on Validation Score-Based Model Aggregation for Federated Learning
    Oensue, Murat Arda
    Kantarci, Burak
    Boukerche, Azzedine
    [J]. ICC 2023-IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, 2023, : 1634 - 1639
  • [8] Depth prior-based stable tensor decomposition for video snow removal
    Li, Yongji
    Wang, Luping
    Jia, Zhenhong
    Yang, Jie
    Kasabov, Nikola
    [J]. Displays, 2024, 84
  • [9] Privacy-Preserving Federated Learning With Malicious Clients and Honest-but-Curious Servers
    Le, Junqing
    Zhang, Di
    Lei, Xinyu
    Jiao, Long
    Zeng, Kai
    Liao, Xiaofeng
    [J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2023, 18 : 4329 - 4344
  • [10] Edge model: An efficient method to identify and reduce the effectiveness of malicious clients in federated learning
    Shahraki, Mahdi
    Bidgoly, Amir Jalaly
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2024, 157 : 459 - 468
12345