Radio frequency fingerprint identification (RFFI) offers a paradigm for the security authentication of the satellite component in automatic identification system (SAT-AIS). This article proposes a data-driven RFFI solution for the SAT-AIS with multiple communication scenarios. Conditional generative adversarial networks (CGANs) embedded with channel estimation can generate numerous realistic samples for data augmentation. Both the generator and the discriminator in CGANs employ deep neural networks to adaptively extract radio frequency fingerprint features, thus enhancing the robustness of this system. Moreover, in light of the dilemma of collecting large datasets, Bayesian meta-learning via variational autoencoder is performed for model training to enable few-shot learning, where only a small number of samples are required to complete the inference for efficient RFFI in multiscenario communications. Experimental results show that the proposed RFFI framework outperforms the existing methods by achieving up to 97.30% accuracy on datasets with signal-to-noise ratios of 10 dB.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Radio Frequency Fingerprint Identification Using Conditional Generative Adversarial Network for SAT-AIS


    Beteiligte:
    Jiang, Qi (Autor:in) / Sha, Jin (Autor:in)


    Erscheinungsdatum :

    01.02.2025


    Format / Umfang :

    1374919 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch






    Synthesis of Passive Human Radio Frequency Signatures via Generative Adversarial Network

    Liu, Jenny / Ewing, Robert / Blasch, Erik et al. | IEEE | 2021


    REALISTIC ULTRASONIC ENVIRONMENT SIMULATION USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS

    Pöpperli, Maximilian / Gulagundi, Raghavendra / Yogamani, Senthil et al. | British Library Conference Proceedings | 2019