Automated Feature Weighting for Network Anomaly Detection

    Research output: Contribution to journalArticle

    Abstract

    A number of network features is used to describe normal and intrusive traffic patterns. However the choice of features is dependent on which pattern to be detected. In order to identify which network features are more important for a particular network pattern, we propose an automated feature weighting method based on a fuzzy subspace approach to vector quantization modeling that can assign a weight to each feature when network models are trained. The proposed method not only increases the detection rate but also reduces false alarm rate as presented in our experiments.
    Original languageEnglish
    Pages (from-to)173-178
    Number of pages6
    JournalInternational Journal of Computer Science and Network Security
    Volume8
    Issue number2
    Publication statusPublished - 2008

    Fingerprint

    Vector quantization
    Experiments

    Cite this

    @article{8f04cb7d3c5b4b67b13a8c70aa23e8f3,
    title = "Automated Feature Weighting for Network Anomaly Detection",
    abstract = "A number of network features is used to describe normal and intrusive traffic patterns. However the choice of features is dependent on which pattern to be detected. In order to identify which network features are more important for a particular network pattern, we propose an automated feature weighting method based on a fuzzy subspace approach to vector quantization modeling that can assign a weight to each feature when network models are trained. The proposed method not only increases the detection rate but also reduces false alarm rate as presented in our experiments.",
    author = "Dat Tran and Wanli Ma and Dharmendra Sharma",
    year = "2008",
    language = "English",
    volume = "8",
    pages = "173--178",
    journal = "International Journal of Computer Science and Network Security",
    issn = "1738-7906",
    number = "2",

    }

    TY - JOUR

    T1 - Automated Feature Weighting for Network Anomaly Detection

    AU - Tran, Dat

    AU - Ma, Wanli

    AU - Sharma, Dharmendra

    PY - 2008

    Y1 - 2008

    N2 - A number of network features is used to describe normal and intrusive traffic patterns. However the choice of features is dependent on which pattern to be detected. In order to identify which network features are more important for a particular network pattern, we propose an automated feature weighting method based on a fuzzy subspace approach to vector quantization modeling that can assign a weight to each feature when network models are trained. The proposed method not only increases the detection rate but also reduces false alarm rate as presented in our experiments.

    AB - A number of network features is used to describe normal and intrusive traffic patterns. However the choice of features is dependent on which pattern to be detected. In order to identify which network features are more important for a particular network pattern, we propose an automated feature weighting method based on a fuzzy subspace approach to vector quantization modeling that can assign a weight to each feature when network models are trained. The proposed method not only increases the detection rate but also reduces false alarm rate as presented in our experiments.

    M3 - Article

    VL - 8

    SP - 173

    EP - 178

    JO - International Journal of Computer Science and Network Security

    JF - International Journal of Computer Science and Network Security

    SN - 1738-7906

    IS - 2

    ER -