Welcome to the InfoSci Platform
Reference Hub4
Novel Intrusion Detection Mechanism with Low Overhead for SCADA Systems

Novel Intrusion Detection Mechanism with Low Overhead for SCADA Systems

Leandros Maglaras, Helge Janicke, Jianmin Jiang, Andrew Crampton
Copyright: © 2017 |Pages: 19
ISBN13: 9781522518297|ISBN10: 1522518290|EISBN13: 9781522518303
DOI: 10.4018/978-1-5225-1829-7.ch009
Cite Chapter Cite Chapter

MLA

Maglaras, Leandros, et al. "Novel Intrusion Detection Mechanism with Low Overhead for SCADA Systems." Security Solutions and Applied Cryptography in Smart Grid Communications, edited by Mohamed Amine Ferrag and Ahmed Ahmim, IGI Global, 2017, pp. 160-178. https://doi.org/10.4018/978-1-5225-1829-7.ch009

APA

Maglaras, L., Janicke, H., Jiang, J., & Crampton, A. (2017). Novel Intrusion Detection Mechanism with Low Overhead for SCADA Systems. In M. Ferrag & A. Ahmim (Eds.), Security Solutions and Applied Cryptography in Smart Grid Communications (pp. 160-178). IGI Global. https://doi.org/10.4018/978-1-5225-1829-7.ch009

Chicago

Maglaras, Leandros, et al. "Novel Intrusion Detection Mechanism with Low Overhead for SCADA Systems." In Security Solutions and Applied Cryptography in Smart Grid Communications, edited by Mohamed Amine Ferrag and Ahmed Ahmim, 160-178. Hershey, PA: IGI Global, 2017. https://doi.org/10.4018/978-1-5225-1829-7.ch009

Export Reference

Mendeley
Favorite

Abstract

SCADA (Supervisory Control and Data Acquisition) systems are a critical part of modern national critical infrastructure (CI) systems. Due to the rapid increase of sophisticated cyber threats with exponentially destructive effects, intrusion detection systems (IDS) must systematically evolve. Specific intrusion detection systems that reassure both high accuracy, low rate of false alarms and decreased overhead on the network traffic must be designed for SCADA systems. In this book chapter we present a novel IDS, namely K-OCSVM, that combines both the capability of detecting novel attacks with high accuracy, due to its core One-Class Support Vector Machine (OCSVM) classification mechanism and the ability to effectively distinguish real alarms from possible attacks under different circumstances, due to its internal recursive k-means clustering algorithm. The effectiveness of the proposed method is evaluated through extensive simulations that are conducted using realistic datasets extracted from small and medium sized HTB SCADA testbeds.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.