arrow
Return

Detecting control system misbehavior by fingerprinting programmable logic controller functionality

delete2019-09-01
delete8
delete
OA
AI
M
Melissa Stockman
D
Dipankar Dwivedi
R
Reinhard Gentz
S
Sean Peisert *
DOI:10.1016/j.ijcip.2019.100306delete
deleteOriginal
deleteShare
deleteSave
View PDF
Abstract

Abstract

En 中文
In recent years, attacks such as the Stuxnet malware have demonstrated that cyberattacks against control systems cause extensive damage. These attacks can result in physical damage to the networked systems under their control. In this paper, we discuss our approach for detecting such attacks by distinguishing between programs running on a programmable logic controller (PLC) without having to monitor communications. Using power signatures generated by an attached, high-frequency power measurement device, we can identify what a PLC is doing and when an attack may have altered what the PLC should be doing. To accomplish this, we generated labeled data for testing our methods and applied feature engineering techniques and machine learning models. The results demonstrate that Random Forests and Convolutional Neural Networks classify programs with up to 98% accuracy for major program differences and 84% accuracy for minor differences. Our results can be used for both online and offline applications. (C) 2019 Elsevier B.V. All rights reserved.
Keywords:
programmable logic controller
cybersecurity
side channels
cyber-physical systems
machine learning

Journal

International Journal of Critical Infrastructure Protection cover
International Journal of Critical Infrastructure Protection
IF:
5.3
Papers:
635
Citations:
1.7K

Organization

U
united states department of energy (doe)
Scholars:
11.3W
Papers: 9.6W
Citations: 17.6W
Cited Papers

Cited Papers

Constitutive Function of the Basic Helix-Loop-Helix/PAS Factor Arnt.
err1995-06-01
err0
errOAAI
errCamilla Antonsson; Velmurugesan Arulampalam; Murray L. Whitelaw; Sven Pettersson; Lorenz Poellinger
errShare
errSave
The effect of nitric acid doping on the optical properties of carbon nanotube films
err2010-09-15
err0
PREAI
errK. Kamarás; Á. Pekker; B. Botka; H. Hu; S. Niyogi; M. E. Itkis; R. C. Haddon
errShare
errSave
errShare
errSave
July temperature during the second millennium reconstructed from Idaho tree rings
err1999-05-15
err0
errOAAI
errFranco Biondi; D. L. Perkins; D. R. Cayan; M. K. Hughes
errShare
errSave
Bayesian Optimization in a Billion Dimensions via Random Embeddings
err2016-02-19
err0
errOAAI
errZiyu Wang; Frank Hutter; Masrour Zoghi; David Matheson; Nando De Feitas
errShare
errSave
no more