Title: Intrusion detection technique using Coarse Gaussian SVM

Authors: Bhoopesh Singh Bhati; C.S. Rai

Addresses: Department of Computer Science and Engineering, Ambedkar Institute of Advanced Communication, Technologies and Research, Geeta Colony, Delhi, India ' USIC&T, Guru Gobind Singh Indraprastha University, Dwarka, New Delhi, India

Abstract: In the new era of internet technology, everybody is transferring data from place to place through the internet. As internet technology is improving, different types of attacks have also increased. To detect the attacks it is important to protect transmitted information. The role of Intrusion Detection System (IDS) is very imperative to detect various types of attacks. Although researchers have proposed numerous theories and methods in the area of IDS, the research in area of intrusion detection is still going on. In this paper, Coarse Gaussian Support Vector Machine (CGSVM) based intrusion detection technique is proposed. The proposed method has four major steps namely, Data Collection, Pre-processing and Studying data, Training and Testing using CGSVM, and Decisions. In implementation, KDDcup99 data sets are used as a benchmark and MATLAB programming environment is used. The results of the simulation are presented by Receiver Operating Characteristics (ROC) and Confusion Matrix. The proposed method achieved detection rates as high 99.99%, 99.95%, 99.53%, 99.19%, 90.57% for DOS, Normal, Probe, R 2 L, U 2 R respectively.

Keywords: information security; intrusion detection; machine learning; Coarse Gaussian SVM; anomaly detection; networks security.

DOI: 10.1504/IJGUC.2021.112458

International Journal of Grid and Utility Computing, 2021 Vol.12 No.1, pp.27 - 32

Received: 04 Apr 2019
Accepted: 28 Jun 2019
Published online: 19 Jan 2021 *

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