Intrusion Detection in Digital Twins for Industrial Control Systems

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingResearchpeer-review

193 Downloads (Pure)

Abstract

Nowadays, the growth of advanced technologies is paving the way for Industrial Control Systems (ICS) and making them more efficient and smarter. However, this makes ICS more connected to communication networks that provide a potential platform for attackers to intrude into the systems and cause damage and catastrophic consequences. In this paper, we propose implementing digital twins that have been equipped with an intrusion detection algorithm. Our novel algorithm is able to detect attacks in a timely manner and also diagnose the type of attack by classification of different types of attacks. With digital twins, which are a new concept in ICS, we have virtual replicas of physical systems so that they precisely mirror the internal behavior of the physical systems. So by placing the intrusion detection algorithm in digital twins, security tests can be done remotely without risking negative impacts on live systems.
Original languageEnglish
Title of host publication2020 International Conference on Software, Telecommunications and Computer Networks (SoftCOM)
PublisherIEEE - Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)978-953-290-099-6
DOIs
Publication statusPublished - 2020
Event28 th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2020) - Hvar, Croatia
Duration: 2020 Sep 172020 Sep 19

Conference

Conference28 th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2020)
Country/TerritoryCroatia
CityHvar
Period2020/09/172020/09/19

Subject classification (UKÄ)

  • Control Engineering

Keywords

  • Intrusion detection
  • Digital twins
  • Industrial control systems

Fingerprint

Dive into the research topics of 'Intrusion Detection in Digital Twins for Industrial Control Systems'. Together they form a unique fingerprint.

Cite this