35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning

Abstract—Industrial control systems are heavily dependant on security and monitoring protocols. For this purpose, monitoring tools take screenshots of control panels for later analysis.Classifying these screenshots into specific groups can be a time-consuming process, but it is crucial for the secur...

ver descrição completa

Detalhes bibliográficos
Autores: Vasco Carofilis, Roberto Andrés, Blanco Medina, Pablo, Jáñez Martino, Francisco, Bennabhaktula, Guru Swaroop, Fidalgo, Eduardo, Prieto Castro, Alejandro, Fidalgo, Víctor
Tipo de documento: capítulo de livro
Data de publicação:2021
País:España
Recursos:Universidad de Castilla-La Mancha
Repositório:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/28645
Acesso em linha:http://doi.org/10.18239/jornadas_2021.34.35
http://hdl.handle.net/10578/28645
Access Level:Acceso aberto
Palavra-chave:Deep Learning
Image Classification
Transfer Learning
Industrial Control System
Fine-tuning
id ES_68cff28bac670a0fdfd0814619c33276
oai_identifier_str oai:ruidera.uclm.es:10578/28645
network_acronym_str ES
network_name_str España
repository_id_str
spelling 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-TuningVasco Carofilis, Roberto AndrésBlanco Medina, PabloJáñez Martino, FranciscoBennabhaktula, Guru SwaroopFidalgo, EduardoPrieto Castro, AlejandroFidalgo, VíctorDeep LearningImage ClassificationTransfer LearningIndustrial Control SystemFine-tuningAbstract—Industrial control systems are heavily dependant on security and monitoring protocols. For this purpose, monitoring tools take screenshots of control panels for later analysis.Classifying these screenshots into specific groups can be a time-consuming process, but it is crucial for the security 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 (IT), Operation Technologies (OT), and others. We compare the results obtained with transfer learning and finetuning on nine convolutional neuronal networks pre-trained with the ImageNet dataset, testing them on a custom CRitical INFrastructure dataset (CRINF-300). Inception-ResNet-V2 obtains the best learning result with an F1-score of 98.32% on CRINF-300, while MobileNet-V1 obtained the best performance-speed tradeoff.Ediciones de la Universidad de Castilla-La Mancha202120212021info:eu-repo/semantics/bookPartapplication/pdfapplication/pdfhttp://doi.org/10.18239/jornadas_2021.34.35http://hdl.handle.net/10578/28645reponame:RUIdeRA. Repositorio Institucional de la UCLMinstname:Universidad de Castilla-La ManchaEspañolinfo:eu-repo/semantics/openAccessoai:ruidera.uclm.es:10578/286452026-05-27T07:36:41Z
dc.title.none.fl_str_mv 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
title 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
spellingShingle 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
Vasco Carofilis, Roberto Andrés
Deep Learning
Image Classification
Transfer Learning
Industrial Control System
Fine-tuning
title_short 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
title_full 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
title_fullStr 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
title_full_unstemmed 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
title_sort 35 Classifying Screenshots of Industrial Control System Using Transfer Learning and Fine-Tuning
dc.creator.none.fl_str_mv Vasco Carofilis, Roberto Andrés
Blanco Medina, Pablo
Jáñez Martino, Francisco
Bennabhaktula, Guru Swaroop
Fidalgo, Eduardo
Prieto Castro, Alejandro
Fidalgo, Víctor
author Vasco Carofilis, Roberto Andrés
author_facet Vasco Carofilis, Roberto Andrés
Blanco Medina, Pablo
Jáñez Martino, Francisco
Bennabhaktula, Guru Swaroop
Fidalgo, Eduardo
Prieto Castro, Alejandro
Fidalgo, Víctor
author_role author
author2 Blanco Medina, Pablo
Jáñez Martino, Francisco
Bennabhaktula, Guru Swaroop
Fidalgo, Eduardo
Prieto Castro, Alejandro
Fidalgo, Víctor
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Deep Learning
Image Classification
Transfer Learning
Industrial Control System
Fine-tuning
topic Deep Learning
Image Classification
Transfer Learning
Industrial Control System
Fine-tuning
description Abstract—Industrial control systems are heavily dependant on security and monitoring protocols. For this purpose, monitoring tools take screenshots of control panels for later analysis.Classifying these screenshots into specific groups can be a time-consuming process, but it is crucial for the security 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 (IT), Operation Technologies (OT), and others. We compare the results obtained with transfer learning and finetuning on nine convolutional neuronal networks pre-trained with the ImageNet dataset, testing them on a custom CRitical INFrastructure dataset (CRINF-300). Inception-ResNet-V2 obtains the best learning result with an F1-score of 98.32% on CRINF-300, while MobileNet-V1 obtained the best performance-speed tradeoff.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021
2021
dc.type.none.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv http://doi.org/10.18239/jornadas_2021.34.35
http://hdl.handle.net/10578/28645
url http://doi.org/10.18239/jornadas_2021.34.35
http://hdl.handle.net/10578/28645
dc.language.none.fl_str_mv Español
language_invalid_str_mv Español
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Ediciones de la Universidad de Castilla-La Mancha
publisher.none.fl_str_mv Ediciones de la Universidad de Castilla-La Mancha
dc.source.none.fl_str_mv reponame:RUIdeRA. Repositorio Institucional de la UCLM
instname:Universidad de Castilla-La Mancha
instname_str Universidad de Castilla-La Mancha
reponame_str RUIdeRA. Repositorio Institucional de la UCLM
collection RUIdeRA. Repositorio Institucional de la UCLM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869409986587656192
score 15.300719

Registros relacionados