אסף שבתאי

אקדמי בכיר

Efficient Cyber Attack Detection in Industrial Control Systems Using Lightweight Neural Networks and PCA

Moshe Kravchik, Asaf Shabtai

Industrial control systems (ICSs) are widely used and vital to industry and society. Their failure can have severe impact on both the economy and human life. Hence, these systems have become an attractive target for physical and cyber attacks alike. In this article, we examine an attack detection method based on simple and lightweight neural networks, namely, 1D convolutional neural networks and autoencoders. We apply these networks to both the time and frequency domains of the data and discuss the pros and cons of each representation approach. The suggested method is evaluated on three popular public datasets, and detection rates matching or exceeding previously published detection results are achieved, while demonstrating a small footprint, short training and detection times, and generality. We also show the effectiveness of PCA, which, given proper data preprocessing and feature selection, can provide high attack detection rates in many settings. Finally, we study the proposed method's robustness against adversarial attacks that exploit inherent blind spots of neural networks to evade detection while achieving their intended physical effect. Our results show that the proposed method is robust to such evasion attacks: in order to evade detection, the attacker is forced to sacrifice the desired physical impact on the system.

שפת פרסום אנגלית
דפים 2179-2197
כתב עת IEEE Transactions on Dependable and Secure Computing
כרך 19
נושא מספר 4
סטטוס פרסום פורסם - 01.01.2022

Keywords

Anomaly detection
adversarial machine learning
adversarial robustness
autoencoders
convolutional neural networks
frequency analysis
industrial control systems

ASJC Scopus subject areas

General Computer Science
Electrical and Electronic Engineering

Sustainable Development Goals

SDG 9 - Industry, Innovation, and Infrastructure
גישה למסמך
10.1109/TDSC.2021.3050101
קבצים וקישורים אחרים
Link to publication in Scopus