Cyber intrusion detection in port bulk handling operations /
Files
(Published version)
Date
2020
Authors
Monks, Kimberley
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
thesis
Citation
Statement of Responsibility
Conference Name
Abstract
Ports that process material in a raw or bulk form are critical to the financial well-being of many nations. This study presents a case study in the application of intrusion detection to a port’s unique context. The thesis extends the analysis of Industrial Control System (ICS) intrusion detection from that applied in other area. Machine Learning and Process Mining approaches are studied. Process Mining uses the physical movement of material through a port to monitor for cyber intrusions. Accuracy is tested using production data. Statistical correlation techniques applied to a calibration data record normal behaviour which is used to monitor a test data set for deviations. The approach provides another view into the ICS, which will complement other types of intrusion detection.
School/Discipline
University of South Australia. UniSA Stem.
UniSA Stem
UniSA Stem
Dissertation Note
Thesis (Masters by research(Computer and Information Science))--University of South Australia, 2020.
Provenance
Copyright 2020 Kimberley Monks.
Description
1 ethesis (ix, 67 pages) :
colour illustrations.
Includes bibliographical references (pages 59-67)
colour illustrations.
Includes bibliographical references (pages 59-67)
Access Status
506 0#$fstar $2Unrestricted online access