Hunting Network Anomalies in a Railway Axle Counter System

Author:

Kuchar Karel1ORCID,Holasova Eva1ORCID,Pospisil Ondrej1ORCID,Ruotsalainen Henri2ORCID,Fujdiak Radek1ORCID,Wagner Adrian3ORCID

Affiliation:

1. Department of Telecommunications, Faculty of Electrical Engineering and Communications, Brno University of Technology, Technicka 12, 616 00 Brno, Czech Republic

2. Institute of IT Security Research, St. Pölten University of Applied Sciences, Campus-Platz 1, 3100 St. Pölten, Austria

3. Department of Rail Technology & Mobility, Carl Ritter von Ghega Institute for Integrated Mobility Research, St. Pölten University of Applied Sciences, Campus-Platz 1, 3100 St. Pölten, Austria

Abstract

This 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. We 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.

Funder

Ministry of the Interior of the Czech Republic

Publisher

MDPI AG

Subject

Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry

Reference33 articles.

1. Directorate-General for Mobility and Transport (European Commission) (2021). EU Transport in Figures: Statistical Pocketbook 2021, European Commission Publications Office.

2. Industry 4.0 Implementation Options in Railway Transport;Klapita;Transp. Res. Procedia,2021

3. Future of industry 5.0 in society: Human-centric solutions, challenges and prospective research areas;Adel;J. Cloud Comput.,2022

4. Heinrich, M., Vieten, J., Arul, T., and Katzenbeisser, S. (2018, January 9–11). Security Analysis of the RaSTA Safety Protocol. Proceedings of the 2018 IEEE International Conference on Intelligence and Security Informatics (ISI), Miami, FL, USA.

5. (2022, November 29). Press release of Deutsche Bahn. Available online: https://www.deutschebahn.com/de/presse/pressestart_zentrales_uebersicht/Zugausfall-in-grossen-Teilen-Norddeutschlands-8960920#.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3