Clustered Federated Learning (FL) is an extension of FL that organizes participating devices into clusters or groups, aiming to train heterogeneous models by grouping devices with diverse data distributions, thus fostering local collaboration within clusters for improved model performance. The increased model diversity introduces challenges stemming from the inherent heterogeneity in functions being modeled (e.g. for targeted advertising in platforms like Facebook), leading to a more natural prevalence of non-independent, non-identically distributed (non-IID) data in clustered FL environments. Moreover, another notable security challenge is that malicious agents can not only change their model updates to the aggregator but also misreport their cluster associations/identities in the clustered FL process. This paper introduces an algorithm called Coordinate-wise Median Clustered (CMC) to address the two challenges of heterogeneous model generation across agents and being robust against malicious agents. This is an algorithm that combines clustering and robust techniques, taking ideas from co-ordinate wise median attack-robust to adapt them to clustered FL. We prove that FedAvg per cluster does not converge under adversarial attacks while our CMC algorithm converges quickly to achieve high accuracy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Robust Clustered Federated Learning Against Malicious Agents


    Contributors:


    Publication date :

    2024-06-24


    Size :

    890468 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Clustered Vehicular Federated Learning: Process and Optimization

    Taik, Afaf / Mlika, Zoubeir / Cherkaoui, Soumaya | IEEE | 2022


    Contract Theory Based Incentive Mechanism for Clustered Vehicular Federated Learning

    Wang, Siyang / Zhao, Haitao / Wen, Wanli et al. | IEEE | 2024


    An Efficient Digital Twin Assisted Clustered Federated Learning Algorithm for Disease Prediction

    Yuan, Xiaoming / Zhang, Jialin / Luo, Jingqi et al. | IEEE | 2022


    Learning-Based Defense against Malicious Unmanned Aerial Vehicles

    Min, Minghui / Xiao, Liang / Xu, Dongjin et al. | IEEE | 2018


    DisBezant: Secure and Robust Federated Learning Against Byzantine Attack in IoT-Enabled MTS

    Ma, Xindi / Jiang, Qi / Shojafar, Mohammad et al. | IEEE | 2023