Title: A hybrid approach for intrusion detection based on machine learning

Authors: Rohit Singh; Mala Kalra; Shano Solanki

Addresses: Department of Computer Science and Engineering, NITTTR, Sector-26, Chandigarh 160019, India ' Department of Computer Science and Engineering, NITTTR, Sector-26, Chandigarh 160019, India ' Department of Computer Science and Engineering, NITTTR, Sector-26, Chandigarh 160019, India

Abstract: With the evolution of internet, network security has emerged as one of the key areas of research. Network security is to safeguard the privacy, availability and integrity of the system. Identification of intrusion is core component to attain overall network security success. Therefore, intrusion detection (ID) is broadly explored by researchers and idea of identification of intrusion has developed into a system, known as intrusion detection system (IDS). IDS focuses on investigation of attacks and offers desirable support for defence management along with information about the intrusion. Several intrusion detection approaches are already proposed to mitigate the impact of intrusion. In this paper, these techniques are discussed to highlight the state-of-the-art and a multilevel hybrid approach based on SVM-Naïve is proposed to predict malicious traffic from the network. Here, KNN along with k-fold cross validation is used to create new high-quality training dataset that outstandingly improved performance of classifiers. Performance of proposed model is evaluated by using standard KDD 1999 Cup dataset. Comparison of proposed model is carried out with existing techniques and it is analysed that its performance is better regarding exactness (99.73%), recognition rate of attack classes (99.81%) and FPR (0.21%).

Keywords: network security; intrusion detection; intrusion detection system; IDS; malicious traffic; multilevel classifiers; KDD 1999 Cup dataset; imbalancing.

DOI: 10.1504/IJSN.2020.111128

International Journal of Security and Networks, 2020 Vol.15 No.4, pp.233 - 242

Received: 09 Nov 2019
Accepted: 10 Nov 2019

Published online: 26 Oct 2020 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article