In this work, we introduce a framework for enhancing secrecy in unmanned aerial vehicle (UAV) aided communication under dynamic attack. We formulate the problem as a secrecy rate maximization then decouple it into secure beamforming and secure UAV trajectory subproblems. We exploit the concept of differential privacy (DP) to design a variational autoencoder (VAE) to perform the secure beamforming. The UAV trajectory subproblem is transformed into a convex quadratically constrained program (QCQP) which is efficiently solved via CVX. The proposed framework shows efficiency in improving the secrecy rate.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Enhancing Secrecy with Differential-Based Framework in UAV Communications Under Dynamic Eavesdroppers


    Beteiligte:
    Kakati, Amayika (Autor:in) / Li, Guoquan (Autor:in)


    Erscheinungsdatum :

    19.04.2024


    Format / Umfang :

    1371534 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch