https://projectswiki.eleceng.adelaide.edu.au/projects/api.php?action=feedcontributions&feedformat=atom&user=A1798511 2026-04-23T12:48:53Z User contributions MediaWiki 1.31.4 https://projectswiki.eleceng.adelaide.edu.au/projects/index.php?title=Projects:2021s1-13352_Graph_Neural_Networks_for_Detecting_Insider_Threats&diff=15968 2021-04-06T06:03:52Z

<p>A1798511: /* Supervisors */</p> <hr /> <div>[[Category:Projects]]<br /> [[Category:Final Year Projects]]<br /> [[Category:2021s1|13352]]<br /> Abstract here<br /> == Introduction ==<br /> 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.<br /> === Project team ===<br /> ==== Project students ====<br /> * Anh Tuan Phu<br /> * Quang Huy Ngo<br /> <br /> ==== Supervisors ====<br /> * Dr. Hong Gunn Chew<br /> * Kyle Millar<br /> * Prof. Hung Nguyen (TRC)<br /> <br /> ==== Advisors ====<br /> *<br /> *<br /> <br /> === Objectives ===<br /> Set of objectives<br /> <br /> == Background ==<br /> === Topic 1 ===<br /> <br /> == Method ==<br /> <br /> == Results ==<br /> <br /> == Conclusion ==<br /> <br /> == References ==<br /> [1] a, b, c, &quot;Simple page&quot;, In Proceedings of the Conference of Simpleness, 2010.<br /> <br /> [2] ..</div>

A1798511 https://projectswiki.eleceng.adelaide.edu.au/projects/index.php?title=Projects:2021s1-13352_Graph_Neural_Networks_for_Detecting_Insider_Threats&diff=15967 2021-04-06T06:03:32Z

<p>A1798511: /* Project students */</p> <hr /> <div>[[Category:Projects]]<br /> [[Category:Final Year Projects]]<br /> [[Category:2021s1|13352]]<br /> Abstract here<br /> == Introduction ==<br /> 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.<br /> === Project team ===<br /> ==== Project students ====<br /> * Anh Tuan Phu<br /> * Quang Huy Ngo<br /> <br /> ==== Supervisors ====<br /> * &lt;Dr. Hong Gunn Chew&gt;<br /> * &lt;Kyle Millar&gt;<br /> * &lt;Prof. Hung Nguyen&gt; (&lt;TRC&gt;)<br /> ==== Advisors ====<br /> *<br /> *<br /> <br /> === Objectives ===<br /> Set of objectives<br /> <br /> == Background ==<br /> === Topic 1 ===<br /> <br /> == Method ==<br /> <br /> == Results ==<br /> <br /> == Conclusion ==<br /> <br /> == References ==<br /> [1] a, b, c, &quot;Simple page&quot;, In Proceedings of the Conference of Simpleness, 2010.<br /> <br /> [2] ..</div>

A1798511 https://projectswiki.eleceng.adelaide.edu.au/projects/index.php?title=Projects:2021s1-13352_Graph_Neural_Networks_for_Detecting_Insider_Threats&diff=15966 2021-04-06T06:03:14Z

<p>A1798511: Created page with &quot;Category:Projects Category:Final Year Projects 13352 Abstract here == Introduction == Insider threats are users with legitimate access to company a...&quot;</p> <hr /> <div>[[Category:Projects]]<br /> [[Category:Final Year Projects]]<br /> [[Category:2021s1|13352]]<br /> Abstract here<br /> == Introduction ==<br /> 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.<br /> === Project team ===<br /> ==== Project students ====<br /> * &lt;Anh Tuan Phu&gt;<br /> * &lt;Quang Huy Ngo&gt;<br /> * &lt;Student 3&#039;s name&gt;<br /> ==== Supervisors ====<br /> * &lt;Dr. Hong Gunn Chew&gt;<br /> * &lt;Kyle Millar&gt;<br /> * &lt;Prof. Hung Nguyen&gt; (&lt;TRC&gt;)<br /> ==== Advisors ====<br /> *<br /> *<br /> <br /> === Objectives ===<br /> Set of objectives<br /> <br /> == Background ==<br /> === Topic 1 ===<br /> <br /> == Method ==<br /> <br /> == Results ==<br /> <br /> == Conclusion ==<br /> <br /> == References ==<br /> [1] a, b, c, &quot;Simple page&quot;, In Proceedings of the Conference of Simpleness, 2010.<br /> <br /> [2] ..</div>

A1798511