Projects:2021s1-13352 Graph Neural Networks for Detecting Insider Threats
Abstract here
Contents
Introduction
Insider threats are users with legitimate access to company assets who use that access, whether maliciously or unintentionally, to cause harm. Insider threats account for 60 percent of recent data breaches. There are major gaps in current insider threat defence with a lack of techniques and solutions to identify insider attack activities in real-time. In this project, we will develop novel Graph Neural Network (GNN) models to learn from network traffic data and user activities to classify network users into security classes. We will start by using GNN to learn baseline of normal behaviour for each user or machine. Deviations from normal activities then can be flagged as abnormal. Using GNNs, deviations will be tracked not only for a specific user but also compared to other users in the same location, with the same job title or job function.
Project team
Project students
- Anh Tuan Phu
- Quang Huy Ngo
Supervisors
- Dr. Hong Gunn Chew
- Kyle Millar
- Prof. Hung Nguyen (TRC)
Advisors
Objectives
Set of objectives
Background
Topic 1
Method
Results
Conclusion
References
[1] a, b, c, "Simple page", In Proceedings of the Conference of Simpleness, 2010.
[2] ..