Projects:2021s1-13352 Graph Neural Networks for Detecting Insider Threats

From Projects
Revision as of 16:33, 6 April 2021 by A1798511 (talk | contribs) (Supervisors)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to: navigation, search

Abstract here

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] ..