Improving Intrusion Detection Using Genetic Algorithm


	Information Technology Journal
	Year: 2013 \| Volume: 12 \| Issue: 11 \| Page No.: 2167-2173 DOI: 10.3923/itj.2013.2167.2173

Improving Intrusion Detection Using Genetic Algorithm

V. Moraveji Hashemi, Z. Muda and W. Yassin

Abstract: Intrusion Detection System (IDS) is one of the key security components in today’s networking environment. A great deal of attention has been recently paid to anomaly detection to accomplish intrusion detection. However, a major problem with this approach is maximizing detection rate and accuracy, as well as minimizing false alarm i.e., inability to correctly discover particular types of attacks. To overcome this problem, a genetic algorithm approach is proposed. Genetic Algorithm (GA) is most frequently employed as a robust technology based on machine learning for designing IDS. GAs are search algorithms which are based on the principles of natural selection and genetics. GA functions on a number of possible solutions using the principle of survival of the fittest with the aim to generate better approximations to solve a particular problem GA is facing. The validity of this approach is verified using Knowledge Discovery and Data Mining Cup 1999 (KDD Cup ’99) dataset. The experimental results demonstrate that the proposed approach outperforms the existing techniques, with the detection rate of attack and false alarm rates of 95.7265 and 4.2735, respectively.

PDF Fulltext XML References Citation Report Citation

RELATED ARTICLES:

•	KM-NEU: An Efficient Hybrid Approach for Intrusion Detection System

•	K-Means Clustering to Improve the Accuracy of Decision Tree Response Classification

•	An Intrusion Detection Model Based on GS-SVM Classifier

•	A K-Means and Naive Bayes Learning Approach for Better Intrusion Detection

How to cite this article:

V. Moraveji Hashemi, Z. Muda and W. Yassin, 2013. Improving Intrusion Detection Using Genetic Algorithm. Information Technology Journal, 12: 2167-2173.

DOI: 10.3923/itj.2013.2167.2173

URL: https://scialert.net/abstract/?doi=itj.2013.2167.2173

COMMENTS

25 November, 2016
pinal:
It's nice. Can you send ur code ??

REPLY

COMMENT ON THIS PAPER

Navigation


		Online First
		Current Issue
		Previous Issues
		Editorial Board
		Submit a Manuscript
		Guide to Authors
		Subscribe to E-alerts

Indexed In


		ASCI-Database
		Asian Digital Library
		Google Scholar

Follow @scialert

Science Alert