A comparison of data mining techniques for intrusion detection

Author

Naidu, R. China Appala ; Avadhani, P.S.

Author_Institution

Dept. of CS & SE, Andhra Univ., Visakhapatnam, India

fYear

2012

fDate

23-25 Aug. 2012

Firstpage

41

Lastpage

44

Abstract

The Expositional increase in the traffic across networks has necessitated the need to detect unauthorized access. In this sense Intrusion Detection has become one of the major research areas In this paper three data mining techniques namely C5.0 Decision Tree, Ripper Rule and Support Vector Machines are studied and compared for the efficiency in detecting the Intrusion, It is found that the C5.0 Decision Tree is efficient than the other two. The data mining tool clementine is used for evaluating this on the KDD99 dataset. The results are also given in this paper.

Keywords

authorisation; computer network security; data mining; decision trees; support vector machines; C5.0 decision tree; KDD99 dataset; data mining techniques; data mining tool clementine; intrusion detection; networks traffic; ripper rule; support vector machines; unauthorized access detection; Data mining; Databases; Electronic publishing; Information services; Internet; Probes; Support vector machines; Decision Tree; Intrusion Detection system; Ripper Rule; Support Vector Machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Communication Control and Computing Technologies (ICACCCT), 2012 IEEE International Conference on

Conference_Location

Ramanathapuram

Print_ISBN

978-1-4673-2045-0

Type

conf

DOI

10.1109/ICACCCT.2012.6320731

Filename

6320731