TY - CONF

T1 - Unsupervised two-class & multi-class support vector machines for abnormal traffic characterization.

AU - Marnerides, Angelos

AU - Pezaros, Dimitrios P.

AU - Kim, Hyun-chul

AU - Hutchison, David

PY - 2009/4/1

Y1 - 2009/4/1

N2 - Although measurement-based real-time traffic classification has received considerable research attention, the timing constraints imposed by the high accuracy requirements and the learning phase of the algorithms employed still remain a challenge. In this paper we propose a measurement-based classification framework that exploits unsupervised learning to accurately categorise network anomalies to specific classes. We introduce the combinatorial use of two-class and multi-class unsupervised Support Vector Machines (SVM)s to first distinguish normal from anomalous traffic and to further classify the latter category to individual groups depending on the nature of the anomaly.

AB - Although measurement-based real-time traffic classification has received considerable research attention, the timing constraints imposed by the high accuracy requirements and the learning phase of the algorithms employed still remain a challenge. In this paper we propose a measurement-based classification framework that exploits unsupervised learning to accurately categorise network anomalies to specific classes. We introduce the combinatorial use of two-class and multi-class unsupervised Support Vector Machines (SVM)s to first distinguish normal from anomalous traffic and to further classify the latter category to individual groups depending on the nature of the anomaly.

KW - networkresilience

KW - anaproject

M3 - Other

T2 - Passive and Active Measurements (PAM) Conference Student Workshop 2009

Y2 - 1 January 2009 through 4 January 2009

ER -