Open AccessNetwork Intrusion Detection Using Multiclass Support Vector Machine
Author(s) -
Arvind Mewada,
Prafful Gedam,
Shamaila Khan,
M. Udayapal Reddy
Publication year - 2010
Publication title -
international journal of computer and communication technology
Language(s) - English
Resource type - Journals
eISSN - 2231-0371
pISSN - 0975-7449
DOI - 10.47893/ijcct.2010.1054
Subject(s) - support vector machine , computer science , multiclass classification , intrusion detection system , artificial intelligence , coding (social sciences) , machine learning , signature (topology) , intrusion , data mining , pattern recognition (psychology) , mathematics , statistics , geometry , geochemistry , geology
Intrusion detection is a topic of interest in current scenario. Statistical IDS overcomes many pitfalls present in signature based IDS. Statistical IDS uses models such as NB, C4.5 etc for classification to detect Intrusions. Multiclass Support Vector Machine is able to perform multiclass classification. This paper shows the performance of MSVM (1-versus-1, 1-versusmany and Error Correcting Output Coding (ECOC)) and it’s variants for statistical NBIDS. This paper explores the performance of MSVM for various categories of attacks.