TBU Publications
Repository of TBU Publications

Optimization of the novelty detection model based on LSTM autoencoder for ICS environment

DSpace Repository

Show simple item record

dc.title Optimization of the novelty detection model based on LSTM autoencoder for ICS environment en
dc.contributor.author Vávra, Jan
dc.contributor.author Hromada, Martin
dc.relation.ispartof Advances in Intelligent Systems and Computing
dc.identifier.issn 2194-5357 Scopus Sources, Sherpa/RoMEO, JCR
dc.identifier.isbn 978-3-03-030328-0
dc.date.issued 2019
utb.relation.volume 1046
dc.citation.spage 306
dc.citation.epage 319
dc.event.title 3rd Conference on Computational Methods in Systems and Software (CoMeSySo)
dc.event.location online
dc.event.sdate 2019-10-03
dc.event.edate 2019-10-05
dc.type conferenceObject
dc.language.iso en
dc.publisher Springer
dc.identifier.doi 10.1007/978-3-030-30329-7_28
dc.relation.uri https://link.springer.com/chapter/10.1007/978-3-030-30329-7_28
dc.subject neural networks en
dc.subject industrial control systems en
dc.subject anomaly detection en
dc.subject genetic algorithm en
dc.description.abstract The recent evolution in cybersecurity shows how vulnerable our technology is. In addition, contemporary society becoming more reliant on “vulnerable technology”. This is especially relevant in case of critical information infrastructure, which is vital to retain the functionality of modern society. Furthermore, the cyber-physical systems as Industrial control systems are an essential part of critical information infrastructure; and therefore, need to be protected. This article presents a comprehensive optimization methodology in the field of industrial network anomaly detection. We introduce a recurrent neural network preparation for a one-class classification task. In order to optimize the recurrent neural network, we adopted a genetic algorithm. The main goal is to create a robust predictive model in an unsupervised manner. Therefore, we use hyperparameter optimization according to the validation loss function, which defines how well the machine learning algorithm models the given data. To achieve this goal, we adopted multiple techniques as data preprocessing, feature reduction, genetic algorithm, etc. © Springer Nature Switzerland AG 2019. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1009479
utb.identifier.obdid 43880005
utb.identifier.scopus 2-s2.0-85075592286
utb.identifier.wok 000564759600028
utb.source d-scopus
dc.date.accessioned 2019-12-20T12:39:22Z
dc.date.available 2019-12-20T12:39:22Z
dc.description.sponsorship Internal Grant Agency [IGA/FAI/2019/002]; Ministry of the Interior of the Czech Republic [VI20172019054]
utb.contributor.internalauthor Vávra, Jan
utb.contributor.internalauthor Hromada, Martin
utb.fulltext.affiliation Jan Vavra, Martin Hromada Faculty of Applied Informatics, Tomas Bata University in Zlin, Zlin, Czechia jvavra@fai.utb.cz
utb.fulltext.dates -
utb.fulltext.sponsorship This work was funded by the Internal Grant Agency (IGA/FAI/2019/002) and supported by the research project VI20172019054 “An analytical software module for the real-time resilience evaluation from point of the converged security”, supported by the Ministry of the Interior of the Czech Republic in the years 2017–2019. Finally, we thank Lemay and Fernandez [14] who provides ICS datasets.
utb.wos.affiliation [Vavra, Jan; Hromada, Martin] Tomas Bata Univ Zlin, Fac Appl Informat, Zlin, Czech Republic
utb.scopus.affiliation Faculty of Applied Informatics, Tomas Bata University in Zlin, Zlin, Czech Republic
utb.fulltext.projects IGA/FAI/2019/002
utb.fulltext.projects VI20172019054
utb.fulltext.faculty Faculty of Applied Informatics
utb.fulltext.faculty Faculty of Applied Informatics
Find Full text

Files in this item

Show simple item record