Improving API Security in the Cloud with AI/ML

Shaji, Rona (2025) Improving API Security in the Cloud with AI/ML. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (874kB) | Preview
Preview	PDF (Configuration Manual) Download (417kB) | Preview

Abstract

Modern cloud applications rely so heavily on APIs; however, just because they rise in popularity, attackers mainly target them right now. Basic security comes from authentication tokens, rate limiting, and rule-based intrusion detection methods. However, these methods do not do much against even advanced security threats. Therefore, it is important for us to look at just how ML is used for securing real time APIs.

The methodology involves the deploying of two detection models: a Random Forest (RF) and a behavioral API data trained neural network autoencoder.

Findings showed the RF model tested accurately at 100% yet lacked generality. The autoencoder, conversely, identified subtle anomalies that conventional techniques failed to identify and reported 96% accuracy and fewer false positives (~3.5%). It concerned more memory demands. Furthermore, it dealt with a greater number of computer requirements. It does still require more computing with memory resources.

ML detection shows more flexibility and responsiveness versus static rules however researchers must carefully profile resources for large deployments.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	17 Jun 2026 08:52
Last Modified:	17 Jun 2026 08:52
URI:	https://norma.ncirl.ie/id/eprint/9376

Actions (login required)

View Item