A3 Book section, Chapters in research books
Industry 4.0 Intelligence under Attack : From Cognitive Hack to Data Poisoning (2018)


Terziyan, V., Golovianko, M., & Gryshko, S. (2018). Industry 4.0 Intelligence under Attack : From Cognitive Hack to Data Poisoning. In K. Dimitrov (Ed.), Cyber Defence in Industry 4.0 Systems and Related Logistics and IT Infrastructures (pp. 110-125). IOS Press. NATO Science for Peace and Security Series D: Information and Communication Security, 51. https://doi.org/10.3233/978-1-61499-888-4-110


JYU authors or editors


Publication details

All authors or editors: Terziyan, Vagan; Golovianko, Mariia; Gryshko, Svitlana

Parent publication: Cyber Defence in Industry 4.0 Systems and Related Logistics and IT Infrastructures

Parent publication editors: Dimitrov, Konstantin

ISBN: 978-1-61499-887-7

Journal or series: NATO Science for Peace and Security Series D: Information and Communication Security

ISSN: 1874-6268

Publication year: 2018

Number in series: 51

Pages range: 110-125

Number of pages in the book: 164

Publisher: IOS Press

Publication country: Netherlands

Publication language: English

DOI: https://doi.org/10.3233/978-1-61499-888-4-110

Publication open access: Not open

Publication channel open access: 

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/60119

Additional information: Proceedings of the NATO Advanced Research Workshop on Cyber Defence in Industry 4.0 Systems and RElated Logistics and IT Infrastructures, Jyväskylä, Finland, 16-21 October 2017.


Abstract

Artificial intelligence is an unavoidable asset of Industry 4.0. Artificial actors participate in real-time decision-making and problem solving in various industrial processes, including planning, production, and management. Their efficiency, as well as intelligent and autonomous behavior is highly dependent on the ability to learn from examples, which creates new vulnerabilities exploited by security threats. Today's disruptive attacks of hackers go beyond system's infrastructures targeting not only hard-coded software or hardware, but foremost data and trained decision models, in order to approach system's intelligence and compromise its work. This paper intends to reveal security threats which are new in the industrial context by observing the latest discoveries in the AI domain. Our focus is data poisoning attacks caused by adversarial training samples and subsequent corruption of machine learning process.
See relevant presentation slides: https://ai.it.jyu.fi/nato/NATO.pptx


Keywords: artificial intelligence; machine learning; industry; data security; hacking; threats

Free keywords: Industry 4.0; security; data poisoning; cognitive hack; cyber-physical systems; value-based decision making


Contributing organizations


Ministry reporting: Yes

VIRTA submission year: 2018

JUFO rating: 1


Last updated on 2024-12-10 at 00:30