Real-Time Cloud-Based Anomaly Detection

Girish Kumar, Gokul (2025) Real-Time Cloud-Based Anomaly Detection. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (512kB) | Preview
Preview	PDF (Configuration Manual) Download (370kB) | Preview

Abstract

The rapid increase in cloud computing has made robust, scalable, and intelligent security solutions more critical than ever. Traditional security systems often struggle to keep pace with the dynamic nature of cloud environments and the increasing sophistication of cyber threats. This research presents the end-to-end design, implementation, and deployment of a scalable, real-time intrusion and anomaly detection system tailored for cloud security. The project's unique contribution lies in its novel integration of a deep learning model with a fully serverless cloud architecture. A Long Short-Term Memory (LSTM) neural network is trained on the comprehensive CICIDS2017 network intrusion dataset to accurately distinguish between benign and malicious network traffic. The trained model is brought to production through a highly innovative and entirely serverless pipeline on Amazon Web Services (AWS), with SageMaker Serverless Inference used as hosting, the AWS Lambda to squeeze requests, and the Amazon API Gateway to publish the functionality as a publicly-accessible endpoint. It would equip the researcher with a detailed technical blueprint, proving a competent, economical, and highly scalable solution, to the new cloud-based cybersecurity headaches.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Punit UNSPECIFIED
Uncontrolled Keywords:	Anomaly Detection; Intrusion Detection; Deep Learning; LSTM; Serverless Architecture; AWS SageMaker; Cloud Security
Subjects:	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 Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 09:44
Last Modified:	26 Mar 2026 09:44
URI:	https://norma.ncirl.ie/id/eprint/9216

Actions (login required)

View Item