Next Article in Journal
Retraction: Kang, S., et al. Achievement of Gradual Conductance Characteristics Based on Interfacial Phase-Change Memory for Artificial Synapse Applications. Electronics 2020, 9, 1268
Next Article in Special Issue
Blockchain Applications to Improve Operation and Security of Transportation Systems: A Survey
Previous Article in Journal
Transparent Control Flow Transfer between CPU and Accelerators for HPC
Previous Article in Special Issue
A Secure Control Design for Networked Control Systems with Linear Dynamics under a Time-Delay Switch Attack
Article

A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data

1
Electrical and Computer Engineering Department, Florida International University, Miami, FL 33174, USA
2
Functional Safety Engineer, Tusimple Co., San Diego, CA 92093, USA
3
Mechanical Engineering Department, Tennessee Technological University, Cookeville, TN 38505, USA
*
Author to whom correspondence should be addressed.
Academic Editor: Rashid Mehmood
Electronics 2021, 10(4), 407; https://doi.org/10.3390/electronics10040407
Received: 1 January 2021 / Revised: 28 January 2021 / Accepted: 1 February 2021 / Published: 8 February 2021
(This article belongs to the Special Issue Security of Cyber-Physical Systems)
Attack detection problems in industrial control systems (ICSs) are commonly known as a network traffic monitoring scheme for detecting abnormal activities. However, a network-based intrusion detection system can be deceived by attackers that imitate the system’s normal activity. In this work, we proposed a novel solution to this problem based on measurement data in the supervisory control and data acquisition (SCADA) system. The proposed approach is called measurement intrusion detection system (MIDS), which enables the system to detect any abnormal activity in the system even if the attacker tries to conceal it in the system’s control layer. A supervised machine learning model is generated to classify normal and abnormal activities in an ICS to evaluate the MIDS performance. A hardware-in-the-loop (HIL) testbed is developed to simulate the power generation units and exploit the attack dataset. In the proposed approach, we applied several machine learning models on the dataset, which show remarkable performances in detecting the dataset’s anomalies, especially stealthy attacks. The results show that the random forest is performing better than other classifier algorithms in detecting anomalies based on measured data in the testbed. View Full-Text
Keywords: machine learning; industrial control systems; anomaly detection; fault detection; intrusion detection system machine learning; industrial control systems; anomaly detection; fault detection; intrusion detection system
Show Figures

Figure 1

MDPI and ACS Style

Mokhtari, S.; Abbaspour, A.; Yen, K.K.; Sargolzaei, A. A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data. Electronics 2021, 10, 407. https://doi.org/10.3390/electronics10040407

AMA Style

Mokhtari S, Abbaspour A, Yen KK, Sargolzaei A. A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data. Electronics. 2021; 10(4):407. https://doi.org/10.3390/electronics10040407

Chicago/Turabian Style

Mokhtari, Sohrab, Alireza Abbaspour, Kang K. Yen, and Arman Sargolzaei. 2021. "A Machine Learning Approach for Anomaly Detection in Industrial Control Systems Based on Measurement Data" Electronics 10, no. 4: 407. https://doi.org/10.3390/electronics10040407

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop