Thiyada Sridharan, Athipan (2023) Streamlining Personalised Vulnerability Analysis and Anomaly Detection through API requests with a Random Forest Model. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (20MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (7MB) | Preview |
Abstract
While cyber threats are rapidly evolving, it is crucial to have effective anomaly detection systems to monitor our server. This research introduces a machine learning-based detector designed to identify anomalies and vulnerability analysis in web applications. By analyzing historical data of known vulnerabilities and monitoring real-time trac, the system distinguishes between normal and malicious activities, ensuring a strong security defence. Integrating this model into a web application allows for an automated, immediate response to potential security threats. The study’s findings suggest that applying machine learning algorithms can significantly decrease the likelihood of overlooking security breaches, thus strengthening web applications against evolving cyber-attacks.
Actions (login required)
![]() |
View Item |