Use this URL to cite or link to this record in EThOS:
Title: Artificial life as a vehicle for anomalies detection on industrial control system : the behaviour of bird swarms and how it can be applied in ICS
Author: Okeke, Michael
ISNI:       0000 0004 8502 8730
Awarding Body: University of South Wales
Current Institution: University of South Wales
Date of Award: 2018
Availability of Full Text:
Access from EThOS:
Access from Institution:
The proliferation of attacks on critical infrastructures in recent time has posed questions on how to secure such systems. Industrial Control Systems (ICS) such as Supervisory Control and Data Acquisition (SCADA) is used on critical infrastructures such as manufacturing industries, nuclear sites, oil and gas industries, locomotives and among others. These systems generate a lot of data and the current detection engine cannot handle such data. This project is a demonstration of an innovative idea titled "Artificial Life as a Vehicle in Detecting Malicious Behaviours on Industrial Control Systems". This provides model framework for detecting malicious activities on Industrial Control System (ICS). The project provides artificial life model for securing ICS. The model is based on the behaviours of swarm of birds. Swarm or flock of birds have some characteristics that worth emulating such as their approach in detecting predator in their environment. These animals are not necessarily very intelligent animal but their approach in group for the detection and avoidance of predator was studied and adopted. Hence, detection in this respect is adopting the flock of bird's approach in detecting predator. The important findings of this project are their individual or single bird action during flight that made them forms group as well as their information transfer from one bird to the entire flock. These are the two vital properties of the flock of birds that enhances their detection of predator. These approaches were modelled for the detection of anomalies on ICS. The model proved that it is possible to apply this approach on ICS and the architecture shows that the model can detect unknown anomalies and handle big data challenges.
Supervisor: Blyth, Andrew Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available