Development and Performance Evaluation of a Dockerized Flask Application for Phishing URL Detection Across AWS and Azure

Murugan, Yamini (2024) Development and Performance Evaluation of a Dockerized Flask Application for Phishing URL Detection Across AWS and Azure. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Businesses today predominantly rely on their online presence and are migrating toward cloud solutions for a cost-efficient pay-as-you-go, scalable, and improved reliability model. However, increased dependence on online platforms has exposed organizations and users to various forms of cyber threats, particularly phishing. Phishing, entices users into making monetary transactions and leak their sensitive information, leading to financial loss and data breaches. To combat this problem, this research proposes a phishing URL detection system utilizing Deep Learning models while leveraging the benefits of cloud technologies to ensure high availability and minimal latency. This Phishing URL detection system utilizes Kaggle dataset for benign and phishing URLs, from which 19 features and 1 labelling feature are extracted to build the final dataset for training the DL models. After feature extraction and preprocessing, CNN, LSTM, and BiLSTM models were built to classify the URLs. The BiLSTM model achieving the highest accuracy of 85% was chosen to build the flask app. Furthermore, the application was made portable and easier to deploy by being containerized using Docker and deployed on AWS Elastic Beanstalk and Azure Container Apps. For load testing, Locust was used to generate the traffic with 2000 concurrent users simulated to join at a rate of five users/second. Finally, the performance was documented using AWS CloudWatch and Azure Monitor, and the results were used to evaluate how both cloud platforms performed under various circumstances, benchmarking the CPU usage, network traffic, latency and load average, to compare the strengths and weaknesses of each platform.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Arun, Shreyas Setlur UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science 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
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	16 Jul 2025 08:30
Last Modified:	16 Jul 2025 08:30
URI:	https://norma.ncirl.ie/id/eprint/8127

Actions (login required)

View Item