Network intrusion detection using meta-heuristic feature selection and cost-sensitive learning
by Ritinder Kaur; Neha Gupta
International Journal of Internet Technology and Secured Transactions (IJITST), Vol. 13, No. 2, 2023

Abstract: In contemporary society, networked computers are playing a pivotal role in dissemination of knowledge and critical data in information systems; ensuring its security has become a challenging task for the network administrators and researchers. Machine learning techniques are extensively used in intrusion detection systems to mine out the extensive network data and extrapolate attack patterns. This paper proposes an intrusion detection framework with a combination of diverse attribute selection algorithms and machine learning algorithms to provide effective intrusion detection. Firstly, the model extracts the most relevant attributes using a hybrid meta-heuristic feature selection algorithm and then applies supervised machine learning algorithms to detect the several attack classes with improved detection accuracy, execution time and error rate. This study used NSL-KDD dataset on the proposed CS-CFSMHA framework with AdaBoost ensemble technique. Cost-sensitive classification was applied which improved the minority class accuracy and the overall accuracy to 81.1%.

Online publication date: Tue, 14-Mar-2023

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Internet Technology and Secured Transactions (IJITST):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com