An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines

An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines

Srinivasa K G
Copyright: © 2013 |Volume: 7 |Issue: 4 |Pages: 16
ISSN: 1930-1650|EISSN: 1930-1669|EISBN13: 9781466635432|DOI: 10.4018/ijisp.2013100104
Cite Article Cite Article

MLA

K G, Srinivasa. "An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines." IJISP vol.7, no.4 2013: pp.37-52. http://doi.org/10.4018/ijisp.2013100104

APA

K G, S. (2013). An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines. International Journal of Information Security and Privacy (IJISP), 7(4), 37-52. http://doi.org/10.4018/ijisp.2013100104

Chicago

K G, Srinivasa. "An Intelligent Network Intrusion Detection System Based on Multi-Modal Support Vector Machines," International Journal of Information Security and Privacy (IJISP) 7, no.4: 37-52. http://doi.org/10.4018/ijisp.2013100104

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Increase in the number of network based transactions for both personal and professional use has made network security gain a significant and indispensable status. The possible attacks that an Intrusion Detection System (IDS) has to tackle can be of an existing type or of an entirely new type. The challenge for researchers is to develop an intelligent IDS which can detect new attacks as efficiently as they detect known ones. Intrusion Detection Systems are rendered intelligent by employing machine learning techniques. In this paper we present a statistical machine learning approach to the IDS using the Support Vector Machine (SVM). Unike conventional SVMs this paper describes a milti model approach which makes use of an extra layer over the existing SVM. The network traffic is modeled into connections based on protocols at various network layers. These connection statistics are given as input to SVM which in turn plots each input vector. The new attacks are identified by plotting them with respect to the trained system. The experimental results demonstrate the lower execution time of the proposed system with high detection rate and low false positive number. The 1999 DARPA IDS dataset is used as the evaluation dataset for both training and testing. The proposed system, SVM NIDS is bench marked with SNORT (Roesch, M. 1999), an open source IDS.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.