Thesis Details

Metody klasifikace síťového provozu

Master's Thesis Student: Jacko Michal Academic Year: 2016/2017 Supervisor: Barabas Maroš, Ing., Ph.D.
English title
Methods for Network Traffic Classification
Language
Czech
Abstract

This paper deals with a problem of detection of network traffic anomaly and classification of network flows. Based on existing methods, paper describes proposal and implementaion of a tool, which can automatically classify network flows. The tool uses CUDA platform for network data processing and computation of network flow metrics using graphics processing unit. Processed flows are subsequently classified by proposed methods for network anomaly detection.

Keywords

anomaly detection, IDS, network security, classification, CUDA, network attacks

Department
Department of Intelligent Systems FIT BUT
Degree Programme
Information Technology, Field of Study Computer Networks and Communication
Files
Status
defended, grade E
Date
21 June 2017
Reviewer
Ovšonka Daniel, Ing.
Committee
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), předseda
Češka Milan, prof. RNDr., CSc. (DITS FIT BUT), člen
Fiedler Petr, doc. Ing., Ph.D. (UAMT FEEC BUT), člen
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Zachariášová Marcela, Ing., Ph.D. (DCSY FIT BUT), člen
Citation
JACKO, Michal. Metody klasifikace síťového provozu. Brno, 2017. Master's Thesis. Brno University of Technology, Faculty of Information Technology. 2017-06-21. Supervised by Barabas Maroš. Available from: https://www.fit.vut.cz/study/thesis/20238/
BibTeX 
@mastersthesis{FITMT20238,
    author = "Michal Jacko",
    type = "Master's thesis",
    title = "Metody klasifikace s\'{i}\v{t}ov\'{e}ho provozu",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2017,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/20238/"
}

Theses

Back to top