Aiming at the problem that traditional machine methods rely on expert experience and the effect of malicious traffic identification is not ideal, a deep learning hybrid model is proposed to detect malicious TLS traffic. The model combines one-dimensional convolutional neural network and two-way long-term and short-term memory network to compress and extract network traffic features from two dimensions of space and time series. At the same time, attention score of output information is extracted by attention mechanism, and traffic identification is carried out by using mixed features obtained by fully connected neural network. Based on the open data set, the experimental results show that the accuracy, recall and F1 value of the model on the test set reach 94.67%, 89.66% and 91.08% respectively, which has good recognition effect.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Malicious TLS Traffic Detection Based on Spatiotemporal Feature Fusion


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Liang, Qilian (editor) / Wang, Wei (editor) / Mu, Jiasong (editor) / Liu, Xin (editor) / Na, Zhenyu (editor) / Qin, Mingyue (author) / Nian, Mei (author) / Zhang, Jun (author) / Chen, Bingcai (author)


    Publication date :

    2022-03-22


    Size :

    8 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    MALICIOUS TRAFFIC DETECTION WITH ANOMALY DETECTION MODELING

    ACHLEITNER STEFAN / XU CHENGCHENG | European Patent Office | 2022

    Free access

    MALICIOUS TRAFFIC DETECTION WITH ANOMALY DETECTION MODELING

    ACHLEITNER STEFAN / XU CHENGCHENG | European Patent Office | 2022

    Free access

    Malicious traffic detection based on GWO-SVM model

    Liu, Lechao / Zhuang, Yan / Gao, Xufei | IEEE | 2022



    Malicious network traffic identification

    European Patent Office | 2016

    Free access