Collaborative anomaly detection in adversarial environments
Project Leader: Sarah Monazam Erfani
Staff: Chris Leckie (CIS), Tansu Alpcan (EE)
Primary Contact: Sarah Monazam Erfani (email@example.com)
Keywords: artificial intelligence; cybersecurity; deep learning; machine learning
Disciplines: Computing and Information Systems,Electrical & Electronic Engineering
The project aims to develop flexible and collaborative anomaly detection mechanisms to identify suspicious behaviour in adversarial environments, where multiple data sources submit their data to a server, in order to detect anomalies with respect to the wider population. By combining data from multiple sources, collaborative anomaly detection aims to improve detection accuracy through the construction of a more robust model of normal behaviour. The application domains include IoT, critical infrastructure, and Software-Defined and Cognitive Radio Networks. The methodology includes deep learning, adversarial machine learning, and optimisation theories.
The interested students should have a solid background in machine learning, programming and mathematics. The project will balance experimental/computational analysis with developing theoretical insights. Successful applicants will benefit from a generous top-up scholarship and potential future employment opportunities.