Hunting Network Anomalies in a Railway Axle Counter System

Simple item page
dc.contributor.authorKuchař, Karelcs
dc.contributor.authorHolasová, Evacs
dc.contributor.authorPospíšil, Ondřejcs
dc.contributor.authorRuotsalainen, Henrics
dc.contributor.authorFujdiak, Radekcs
dc.contributor.authorWagner, Adriancs
dc.coverage.issue6cs
dc.coverage.volume23cs
dc.date.accessioned2023-07-21T06:53:45Z
dc.date.available2023-07-21T06:53:45Z
dc.date.issued2023-03-14cs
dc.description.abstractThis paper presents a comprehensive investigation of machine learning-based intrusion detection methods to reveal cyber attacks in railway axle counting networks. In contrast to the state-of-the-art works, our experimental results are validated with testbed-based real-world axle counting components. Furthermore, we aimed to detect targeted attacks on axle counting systems, which have higher impacts than conventional network attacks. W present a comprehensive investigation of machine learning-based intrusion detection methods to reveal cyber attacks in railway axle counting networks. According to our findings, the proposed machine learning-based models were able to categorize six different network states (normal and under attack). The overall accuracy of the initial models was ca. 70–100% for the test data set in laboratory conditions. In operational conditions, the accuracy decreased to under 50%. To increase the accuracy, we introduce a novel input data-preprocessing method with the denoted gamma parameter. This increased the accuracy of the deep neural network model to 69.52% for six labels, 85.11% for five labels, and 92.02% for two labels. The gamma parameter also removed the dependence on the time series, enabled relevant classification of data in the real network, and increased the accuracy of the model in real operations. This parameter is influenced by simulated attacks and, thus, allows the classification of traffic into specified classes.en
dc.formattextcs
dc.format.extent1-19cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationSENSORS. 2023, vol. 23, issue 6, p. 1-19.en
dc.identifier.doi10.3390/s23063122cs
dc.identifier.issn1424-8220cs
dc.identifier.orcid0000-0002-5972-9037cs
dc.identifier.orcid0000-0002-5584-2948cs
dc.identifier.orcid0000-0002-8347-4847cs
dc.identifier.orcid0000-0002-8319-0633cs
dc.identifier.other183121cs
dc.identifier.researcheridABG-4089-2020cs
dc.identifier.researcheridABG-5140-2020cs
dc.identifier.scopus56610269000cs
dc.identifier.urihttp://hdl.handle.net/11012/213556
dc.language.isoencs
dc.publisherMDPIcs
dc.relation.ispartofSENSORScs
dc.relation.urihttps://www.mdpi.com/1424-8220/23/6/3122cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1424-8220/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectattack classificationen
dc.subjectaxle counteren
dc.subjectfeature selectionen
dc.subjectICSen
dc.subjectneural networken
dc.subjectOTen
dc.subjectrailwayen
dc.subjecttestbed threaten
dc.titleHunting Network Anomalies in a Railway Axle Counter Systemen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-183121en
sync.item.dbtypeVAVen
sync.item.insts2023.08.09 16:54:40en
sync.item.modts2023.08.09 16:16:14en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav telekomunikacícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
sensors2303122v2.pdf
Size:
763.49 KB
Format:
Adobe Portable Document Format
Description:
sensors2303122v2.pdf
Download
Collections
Ústav telekomunikací