Skip to Main content Skip to Navigation
Conference papers

Detecting Anomalous Programmable Logic Controller Events Using Machine Learning

Abstract : Industrial control system failures can be hazardous to human lives and the environment. Programmable logic controllers are major components of industrial control systems that are used across the critical infrastructure. Attack and accident investigations involving programmable logic controllers rely on forensic techniques to establish the root causes and to develop mitigation strategies. However, programmable logic controller forensics is a challenging task, primarily because of the lack of system logging. This chapter proposes a novel methodology that logs the values of relevant memory addresses used by a programmable logic controller program along with their timestamps. Machine learning techniques are applied to the logged data to identify anomalous or abnormal programmable logic controller operations. An application of the methodology to a simulated traffic light control system demonstrates its effectiveness in performing forensic investigations of programmable logic controllers.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Friday, February 23, 2018 - 3:51:02 PM
Last modification on : Friday, February 23, 2018 - 3:51:47 PM
Long-term archiving on: : Friday, May 25, 2018 - 6:19:03 AM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Ken Yau, Kam-Pui Chow. Detecting Anomalous Programmable Logic Controller Events Using Machine Learning. 13th IFIP International Conference on Digital Forensics (DigitalForensics), Jan 2017, Orlando, FL, United States. pp.81-94, ⟨10.1007/978-3-319-67208-3_5⟩. ⟨hal-01716409⟩



Record views


Files downloads