Multi Class Machine Learning Algorithms for Intrusion Detection - A Performance Study

Manjula C. Belavagi*, Balachandra Muniyal

*Corresponding author for this work

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    11 Citations (Scopus)

    Abstract

    Advancement of the network technology has increased our dependency on the Internet. Hence the security of the network plays a very important role. The network intrusions can be identified using Intrusion Detection System (IDS). Machine learning algorithms are used to predict the network behavior as intrusion or normal. This paper discusses the prediction analysis of different supervised machine learning algorithms namely Logistic Regression, Gaussian Naive Bayes, Support Vector Machine and Random Forest on NSL-KDD dataset. These machine learning classification techniques are used to predict the four different types of attacks namely Denial of Service attack, Remote to Local (R2L), Probe and User to Root(U2R) attacks using multi-class classification technique.

    Original languageEnglish
    Title of host publicationSecurity in Computing and Communications - 5th International Symposium, SSCC 2017, Proceedings
    EditorsGregorio Martinez Perez, Felix Gomez Marmol, Sabu M. Thampi, Carlos Becker Westphall, Chun I. Fan, Jiankun Hu
    PublisherSpringer Verlag
    Pages170-178
    Number of pages9
    ISBN (Print)9789811068973
    DOIs
    Publication statusPublished - 01-01-2017
    Event5th International Symposium on Security in Computing and Communications, SSCC 2017 - Manipal, India
    Duration: 13-09-201716-09-2017

    Publication series

    NameCommunications in Computer and Information Science
    Volume746
    ISSN (Print)1865-0929

    Conference

    Conference5th International Symposium on Security in Computing and Communications, SSCC 2017
    Country/TerritoryIndia
    CityManipal
    Period13-09-1716-09-17

    All Science Journal Classification (ASJC) codes

    • General Computer Science
    • General Mathematics

    Fingerprint

    Dive into the research topics of 'Multi Class Machine Learning Algorithms for Intrusion Detection - A Performance Study'. Together they form a unique fingerprint.

    Cite this