Anomaly detection in SCADA systems: a network based approach

R.R.R. Barbosa

Abstract

Supervisory Control and Data Acquisition (SCADA) networks are commonly deployed to aid the operation of large industrial facilities, such as water treatment facilities. Historically, these networks were composed by special-purpose embedded devices communicating through proprietary protocols. However, modern deployments commonly make use of commercial off-the-shelf devices and standard communication protocols, such as TCP/IP. Furthermore, these networks are becoming increasingly interconnected, allowing communication with corporate networks and even the Internet. As a result, SCADA networks become vulnerable to cyber attacks, being exposed to the same threats that plague traditional IT systems. In our view, measurements play an essential role in validating results in network research; therefore, our first objective is to understand how SCADA networks are utilized in practice. To this end, we provide the first comprehensive analysis of real-world SCADA traffic. We analyze five network packet traces collected at four different critical infrastructures: two water treatment facilities, one gas utility, and one electricity and gas utility. We show, for instance, that exiting network traffic models developed for traditional IT networks cannot be directly applied to SCADA network traffic. We also confirm two SCADA traffic characteristics: the stable connection matrix and the traffic periodicity, and propose two intrusion detection approaches that exploit them. In order to exploit the stable connection matrix, we investigate the use of whitelists at the flow level. We show that flow whitelists have a manageable size, considering the number of hosts in the network, and that it is possible to overcome the main sources of instability in the whitelists. In order to exploit the traffic periodicity, we focus our attention to connections used to retrieve data from devices in the field network. We propose PeriodAnalyzer, an approach that uses deep packet inspection to automatically identify the different messages and the frequency at which they are issued. Once such normal behavior is learned, PeriodAnalyzer can be used to detect data injection and Denial of Service attacks.
Original languageEnglish
Awarding Institution
  • University of Twente
Supervisors/Advisors
  • Pras, Aiko , Supervisor
  • Haverkort, Boudewijn R.H.M., Supervisor
Date of Award2 Apr 2014
Place of PublicationEnschede
Publisher
Print ISBNs978-90-365-3645-5
DOIs
StatePublished - 2 Apr 2014

Fingerprint

Data acquisition
Water treatment
Gases
Critical infrastructures
SCADA systems
Packet networks
Intrusion detection
Electricity
Inspection
Internet
Communication
Denial-of-service attack

Keywords

  • METIS-303169
  • IR-90271

Cite this

Barbosa, R. R. R. (2014). Anomaly detection in SCADA systems: a network based approach Enschede: Universiteit Twente DOI: 10.3990/1.9789036536455
Barbosa, R.R.R.. / Anomaly detection in SCADA systems: a network based approach. Enschede : Universiteit Twente, 2014. 194 p.
@misc{208db0dc8f44403f9682c4369eccdc3f,
title = "Anomaly detection in SCADA systems: a network based approach",
abstract = "Supervisory Control and Data Acquisition (SCADA) networks are commonly deployed to aid the operation of large industrial facilities, such as water treatment facilities. Historically, these networks were composed by special-purpose embedded devices communicating through proprietary protocols. However, modern deployments commonly make use of commercial off-the-shelf devices and standard communication protocols, such as TCP/IP. Furthermore, these networks are becoming increasingly interconnected, allowing communication with corporate networks and even the Internet. As a result, SCADA networks become vulnerable to cyber attacks, being exposed to the same threats that plague traditional IT systems. In our view, measurements play an essential role in validating results in network research; therefore, our first objective is to understand how SCADA networks are utilized in practice. To this end, we provide the first comprehensive analysis of real-world SCADA traffic. We analyze five network packet traces collected at four different critical infrastructures: two water treatment facilities, one gas utility, and one electricity and gas utility. We show, for instance, that exiting network traffic models developed for traditional IT networks cannot be directly applied to SCADA network traffic. We also confirm two SCADA traffic characteristics: the stable connection matrix and the traffic periodicity, and propose two intrusion detection approaches that exploit them. In order to exploit the stable connection matrix, we investigate the use of whitelists at the flow level. We show that flow whitelists have a manageable size, considering the number of hosts in the network, and that it is possible to overcome the main sources of instability in the whitelists. In order to exploit the traffic periodicity, we focus our attention to connections used to retrieve data from devices in the field network. We propose PeriodAnalyzer, an approach that uses deep packet inspection to automatically identify the different messages and the frequency at which they are issued. Once such normal behavior is learned, PeriodAnalyzer can be used to detect data injection and Denial of Service attacks.",
keywords = "METIS-303169, IR-90271",
author = "R.R.R. Barbosa",
year = "2014",
month = "4",
doi = "10.3990/1.9789036536455",
isbn = "978-90-365-3645-5",
publisher = "Universiteit Twente",
school = "University of Twente",

}

Barbosa, RRR 2014, 'Anomaly detection in SCADA systems: a network based approach', University of Twente, Enschede. DOI: 10.3990/1.9789036536455

Anomaly detection in SCADA systems: a network based approach. / Barbosa, R.R.R.

Enschede : Universiteit Twente, 2014. 194 p.

Research output: ScientificPhD Thesis - Research UT, graduation UT

TY - THES

T1 - Anomaly detection in SCADA systems: a network based approach

AU - Barbosa,R.R.R.

PY - 2014/4/2

Y1 - 2014/4/2

N2 - Supervisory Control and Data Acquisition (SCADA) networks are commonly deployed to aid the operation of large industrial facilities, such as water treatment facilities. Historically, these networks were composed by special-purpose embedded devices communicating through proprietary protocols. However, modern deployments commonly make use of commercial off-the-shelf devices and standard communication protocols, such as TCP/IP. Furthermore, these networks are becoming increasingly interconnected, allowing communication with corporate networks and even the Internet. As a result, SCADA networks become vulnerable to cyber attacks, being exposed to the same threats that plague traditional IT systems. In our view, measurements play an essential role in validating results in network research; therefore, our first objective is to understand how SCADA networks are utilized in practice. To this end, we provide the first comprehensive analysis of real-world SCADA traffic. We analyze five network packet traces collected at four different critical infrastructures: two water treatment facilities, one gas utility, and one electricity and gas utility. We show, for instance, that exiting network traffic models developed for traditional IT networks cannot be directly applied to SCADA network traffic. We also confirm two SCADA traffic characteristics: the stable connection matrix and the traffic periodicity, and propose two intrusion detection approaches that exploit them. In order to exploit the stable connection matrix, we investigate the use of whitelists at the flow level. We show that flow whitelists have a manageable size, considering the number of hosts in the network, and that it is possible to overcome the main sources of instability in the whitelists. In order to exploit the traffic periodicity, we focus our attention to connections used to retrieve data from devices in the field network. We propose PeriodAnalyzer, an approach that uses deep packet inspection to automatically identify the different messages and the frequency at which they are issued. Once such normal behavior is learned, PeriodAnalyzer can be used to detect data injection and Denial of Service attacks.

AB - Supervisory Control and Data Acquisition (SCADA) networks are commonly deployed to aid the operation of large industrial facilities, such as water treatment facilities. Historically, these networks were composed by special-purpose embedded devices communicating through proprietary protocols. However, modern deployments commonly make use of commercial off-the-shelf devices and standard communication protocols, such as TCP/IP. Furthermore, these networks are becoming increasingly interconnected, allowing communication with corporate networks and even the Internet. As a result, SCADA networks become vulnerable to cyber attacks, being exposed to the same threats that plague traditional IT systems. In our view, measurements play an essential role in validating results in network research; therefore, our first objective is to understand how SCADA networks are utilized in practice. To this end, we provide the first comprehensive analysis of real-world SCADA traffic. We analyze five network packet traces collected at four different critical infrastructures: two water treatment facilities, one gas utility, and one electricity and gas utility. We show, for instance, that exiting network traffic models developed for traditional IT networks cannot be directly applied to SCADA network traffic. We also confirm two SCADA traffic characteristics: the stable connection matrix and the traffic periodicity, and propose two intrusion detection approaches that exploit them. In order to exploit the stable connection matrix, we investigate the use of whitelists at the flow level. We show that flow whitelists have a manageable size, considering the number of hosts in the network, and that it is possible to overcome the main sources of instability in the whitelists. In order to exploit the traffic periodicity, we focus our attention to connections used to retrieve data from devices in the field network. We propose PeriodAnalyzer, an approach that uses deep packet inspection to automatically identify the different messages and the frequency at which they are issued. Once such normal behavior is learned, PeriodAnalyzer can be used to detect data injection and Denial of Service attacks.

KW - METIS-303169

KW - IR-90271

U2 - 10.3990/1.9789036536455

DO - 10.3990/1.9789036536455

M3 - PhD Thesis - Research UT, graduation UT

SN - 978-90-365-3645-5

PB - Universiteit Twente

ER -

Barbosa RRR. Anomaly detection in SCADA systems: a network based approach. Enschede: Universiteit Twente, 2014. 194 p. Available from, DOI: 10.3990/1.9789036536455