2006 | OriginalPaper | Chapter
Network Intrusion Detection Using Statistical Probability Distribution
Authors : Gil-Jong Mun, Yong-Min Kim, DongKook Kim, Bong-Nam Noh
Published in: Computational Science and Its Applications - ICCSA 2006
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
It is very difficult to select useful measures and to generate patterns detecting attacks from network. Patterns to detect intrusions are usually generated by expert’s experiences that need a lot of man-power, management expense and time. This paper proposes the statistical methods for detecting attacks without expert’s experiences. The methods are to select the detection measures from features of network connections and to detect attacks. We extracted normal and each attack data from network connections, and selected the measures for detecting attacks by relative entropy. Also we made probability patterns and detected attacks by likelihood ratio. The detection rates and the false positive rates were controlled by the different threshold in the method. We used KDD CUP 99 dataset to evaluate the performance of the proposed methods.