Latent Dirichlet Allocation (LDA) and Variational Inference are applied in near real-time to detect anomalies in ground vehicle network traffic for a ground vehicle network. The technical approach, that utilizes the Natural Language Processing (NLP) technique to detect potential malicious attacks and network configuration issues, is described and the results of a proof of concept implementation are provided. Potential use cases for applying the technique in the aircraft and avionics domain are provided.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Latent Dirichlet Allocation (LDA) for Anomaly Detection in Avionics Networks


    Contributors:


    Publication date :

    2020-10-11


    Size :

    1159986 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Traffic Sign Classification Base on Latent Dirichlet Allocation

    Song, Lei / Liu, Zheyuan / Zhang, Xiaoteng et al. | Springer Verlag | 2018


    Image tag refinement by regularized latent Dirichlet allocation

    Wang, J. / Zhou, J. / Xu, H. et al. | British Library Online Contents | 2014


    Measurement analysis and anomaly detection (military avionics testing)

    Barker, C.R. jun. / Barker, C.R. | Tema Archive | 2003



    Wavelength Allocation Strategies in Optically Switched Networks for Avionics

    Reardon, C.B. / Profumo, J.D. / George, A.D. | IEEE | 2006