Next Article in Journal
A Persona-Based Approach for Identifying Accessibility Issues in Elderly and Disabled Users’ Interaction with Home Appliances
Next Article in Special Issue
Cyber Ranges and TestBeds for Education, Training, and Research
Previous Article in Journal
Effect of Impact Velocity, Flooring Material, and Trochanteric Soft-Tissue Quality on Acetabular Fracture during a Sideways Fall: A Parametric Finite Element Approach
Previous Article in Special Issue
On Combining Static, Dynamic and Interactive Analysis Security Testing Tools to Improve OWASP Top Ten Security Vulnerability Detection in Web Applications
Article

Detecting Vulnerabilities in Critical Infrastructures by Classifying Exposed Industrial Control Systems Using Deep Learning

1
Department of Electrical, Systems and Automation, Universidad de León, 24071 León, Spain
2
INCIBE (Spanish National Cybersecurity Institute), 24005 León, Spain
*
Author to whom correspondence should be addressed.
Appl. Sci. 2021, 11(1), 367; https://doi.org/10.3390/app11010367
Received: 29 November 2020 / Revised: 24 December 2020 / Accepted: 28 December 2020 / Published: 1 January 2021
(This article belongs to the Special Issue Cyber Security of Critical Infrastructures)
Industrial control systems depend heavily on security and monitoring protocols. Several tools are available for this purpose, which scout vulnerabilities and take screenshots of various control panels for later analysis. However, they do not adequately classify images into specific control groups, which is crucial for security-based tasks performed by manual operators. To solve this problem, we propose a pipeline based on deep learning to classify snapshots of industrial control panels into three categories: internet technologies, operation technologies, and others. More specifically, we compare the use of transfer learning and fine-tuning in convolutional neural networks (CNNs) pre-trained on ImageNet to select the best CNN architecture for classifying the screenshots of industrial control systems. We propose the critical infrastructure dataset (CRINF-300), which is the first publicly available information technology (IT)/operational technology (OT) snapshot dataset, with 337 manually labeled images. We used the CRINF-300 to train and evaluate eighteen different pipelines, registering their performance under CPU and GPU environments. We found out that the Inception-ResNet-V2 and VGG16 architectures obtained the best results on transfer learning and fine-tuning, with F1-scores of 0.9832 and 0.9373, respectively. In systems where time is critical and the GPU is available, we recommend using the MobileNet-V1 architecture, with an average time of 0.03 s to process an image and with an F1-score of 0.9758. View Full-Text
Keywords: deep learning; image classification; transfer learning; industrial control system; fine-tuning deep learning; image classification; transfer learning; industrial control system; fine-tuning
Show Figures

Figure 1

MDPI and ACS Style

Blanco-Medina, P.; Fidalgo, E.; Alegre, E.; Vasco-Carofilis, R.A.; Jañez-Martino, F.; Villar, V.F. Detecting Vulnerabilities in Critical Infrastructures by Classifying Exposed Industrial Control Systems Using Deep Learning. Appl. Sci. 2021, 11, 367. https://doi.org/10.3390/app11010367

AMA Style

Blanco-Medina P, Fidalgo E, Alegre E, Vasco-Carofilis RA, Jañez-Martino F, Villar VF. Detecting Vulnerabilities in Critical Infrastructures by Classifying Exposed Industrial Control Systems Using Deep Learning. Applied Sciences. 2021; 11(1):367. https://doi.org/10.3390/app11010367

Chicago/Turabian Style

Blanco-Medina, Pablo, Eduardo Fidalgo, Enrique Alegre, Roberto A. Vasco-Carofilis, Francisco Jañez-Martino, and Victor F. Villar 2021. "Detecting Vulnerabilities in Critical Infrastructures by Classifying Exposed Industrial Control Systems Using Deep Learning" Applied Sciences 11, no. 1: 367. https://doi.org/10.3390/app11010367

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