Efficient Feature Grouping for IDS Using Clustering Algorithms in Detecting Known/Unknown Attacks

Authored by: Ravishanker , Monica Sood , Prikshat Angra , Sahil Verma , Kavita , NZ Jhanjhi

Information Security Handbook

Print publication date:  February  2022
Online publication date:  February  2022

Print ISBN: 9780367365721
eBook ISBN: 9780367808228
Adobe ISBN:


 Download Chapter



In this paper, various feature-grouping techniques are analyzed, along with the machine-learning approaches used to investigate their accuracy. Real-time traffic can be monitored for network attacks, and this monitoring can find both the extrusion and the intrusion traffic. The main aim is to identify network attacks for providing future-proof software solutions such that false alarms could be reduced and a more secure network made. The extrusion traffic detects attacks within the network and movement of data out from the network, whereas the intrusion-detection system will monitor the incoming packets of data in the network. Thus, these systems monitor all the traffic inside as well as outside and provide a better solution for the entire system. The rules in the snort would also be optimized for better detection purposes. In this paper, an algorithm is proposed to enhance the chances to detect intrusion and will perform efficient and optimized data delivery in internal and external network. The proposed work will add a trust parameter to IDS by learning attack patterns in future. This work can further be extended to the application level where decentralized nodes can be added to block-chain techniques to add trust among the newly connected and adjoining nodes.

Search for more...
Back to top

Use of cookies on this website

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more in our Privacy Policy. By continuing to use the site you are agreeing to our use of cookies.