A Study on Classification Techniques for Network Intrusion Detection

S. Kaplantzis and N. Mani (Australia)


Artificial neural networks, K-means Classifier, Network in trusion detection, Support vector machines.


Computer systems vulnerabilities such as software bugs are often exploited by malicious users to intrude into informa tion systems. With the recent growth of the Internet such security limitations are becoming more and more pressing. One commonly used defense measure against such mali cious attacks in the Internet are Intrusion Detection Sys tems (IDSs). In this paper, we compare the ability of three clas sification techniques (k-means classifiers, neural networks and support vector machines) to perform for network intru sion detection applications. The results indicate that Sup port Vector Machines train in the shortest amount of time with an acceptable accuracy whilst Neural Networks ex hibit high accuracy at the cost of long training times.

Important Links:

Go Back