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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:


    Publication date :

    2024-04-19


    Size :

    1371534 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English