Intelligent intrusion detection system using log cluster decision tree detection mitigation in complex event processing
by S. Sandosh; V. Govindasamy; G. Akila
International Journal of Internet Technology and Secured Transactions (IJITST), Vol. 11, No. 4, 2021

Abstract: The world of technology largely engages on the networks that provide the vast amount of data for the user all around the world. The networks can be of different domains that includes education, market or even defence. Hence the network has to be secure against any attacks that lead to intrusion. For securing the networks, several intrusion detection systems (IDS) are developed, however the possibility of intrusion remains in the networks. In the current work, we propose the novel intelligent IDS with log cluster decision tree detection mitigation (IIDS-LCDTDM) technique in complex event processing environment, an extension of our previous work. The novel system comprises of three major algorithms, attribute greedy stepwise selection, two-mean-log cluster along with tree detection, and mitigation algorithm. The gure6percent dataset is used to evaluate the proposed algorithm for various performance metrics using Java/J2EE software. From the evaluation result, the proposed system provided the accuracy of 99.987%, which was better than our previous model with 99.9463%.

Online publication date: Sun, 01-Aug-2021

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