In recent years, the privacy-protecting framework Differential Privacy (DP) has achieved remarkable success and has been widely studied. However, there is a lack of work on DP in the area of Federated Continual Learning (FCL), which is a combination of Federated Learning (FL) and Continual Learning (CL). This paper presents a formal definition of DP-FCL and evaluates several DP-FCL methods based on Gaussian DP (GDP) and Individual DP (IDP). The experimental results indicate that gradient modification based CL strategies are not practical in DP-FCL. To the best of our knowledge, this is the first work to experimentally study DP-FCL, which can provide a reference for future research in this area.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Evaluating Differential Privacy in Federated Continual Learning


    Beteiligte:
    Ouyang, Junyan (Autor:in) / Han, Rui (Autor:in) / Liu, Chi Harold (Autor:in)


    Erscheinungsdatum :

    10.10.2023


    Format / Umfang :

    1968661 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Towards Continual Federated Learning of Monocular Depth for Autonomous Vehicles

    Soares, Elton F. de S. / Campos, Carlos Alberto V. | IEEE | 2024



    Evaluating the Impact of Privacy-Preserving Federated Learning on CAN Intrusion Detection

    Digregorio, Gabriele / Cainazzo, Elisabetta / Longari, Stefano et al. | IEEE | 2024


    A Joint Communication and Learning Design for Secure Federated Learning with Differential Privacy

    Lin, Licheng / Yang, Zhaohui / Yang, Qianqian et al. | IEEE | 2024


    Federated Forests With Differential Privacy for Distributed Wearable Sensors

    Favero, Manuele / Marchioro, Thomas / Schiavo, Chiara | IEEE | 2024