dc.contributor.author |
Jayasekara, Gayana |
|
dc.date.accessioned |
2025-06-06T05:55:14Z |
|
dc.date.available |
2025-06-06T05:55:14Z |
|
dc.date.issued |
2024 |
|
dc.identifier.citation |
Jayasekara, Gayana (2024) EventGuard: Anomaly Detection in Windows Event Logs through Automated Machine Learning Techniques. BSc. Dissertation, Informatics Institute of Technology |
en_US |
dc.identifier.issn |
20200672 |
|
dc.identifier.uri |
http://dlib.iit.ac.lk/xmlui/handle/123456789/2460 |
|
dc.description.abstract |
"EventGuard enhances Windows event log analysis for security by employing machine learning,
particularly deep learning-based solutions. It evaluates five widely used neural networks within
three cutting-edge techniques for log-based anomaly identification. This proactive defense against
cyberattacks enables early risk identification and response, contributing valuable insights to the
field and emphasizing the critical role of log analysis in addressing evolving security threats.
The methodology of EventGuard revolves around assessing machine learning modules, focusing
on deep learning-based solutions. It explores the effectiveness of five commonly deployed neural
networks within three techniques designed for log-based anomaly identification. EventGuard not
only provides proactive defense against cyber threats but also enhances the overall security posture
of computer systems. By contributing insights to anomaly identification in Windows event logs,
EventGuard underscores the significance of log analysis in mitigating security threats." |
en_US |
dc.language.iso |
en |
en_US |
dc.subject |
Windows Event Logs |
en_US |
dc.subject |
Automated Machine Learning |
en_US |
dc.subject |
Feature Engineering |
en_US |
dc.title |
EventGuard: Anomaly Detection in Windows Event Logs through Automated Machine Learning Techniques. |
en_US |
dc.type |
Thesis |
en_US |