Combining ensemble methods and social network metrics for improving accuracy of OCSVM on intrusion detection in SCADA systems

TL;DR

This paper enhances intrusion detection in SCADA systems by combining ensemble methods with social network metrics to improve the accuracy of one-class SVMs, validated through extensive simulations on real cyber attack data.

Contribution

It introduces a novel approach that integrates ensemble techniques and social network metrics with OCSVM for more accurate intrusion detection in SCADA systems.

Findings

Improved detection accuracy over standard OCSVM methods.

Effective in identifying various types of cyber attacks.

Validated through simulations on real attack data.

Abstract

Modern Supervisory Control and Data Acquisition SCADA systems used by the electric utility industry to monitor and control electric power generation, transmission and distribution are recognized today as critical components of the electric power delivery infrastructure. SCADA systems are large, complex and incorporate increasing numbers of widely distributed components. The presence of a real time intrusion detection mechanism, which can cope with different types of attacks, is of great importance, in order to defend a system against cyber attacks This defense mechanism must be distributed, cheap and above all accurate, since false positive alarms, or mistakes regarding the origin of the intrusion mean severe costs for the system. Recently an integrated detection mechanism, namely IT-OCSVM was proposed, which is distributed in a SCADA network as a part of a distributed intrusion detection system (IDS), providing accurate data about the origin and the time of an intrusion. In this paper we also analyze the architecture of the integrated detection mechanism and we perform extensive simulations based on real cyber attacks in a small SCADA testbed in order to evaluate the performance of the proposed mechanism.