Improving Cloud Security with Real-Time Detection of APT Attacks Using Advanced Deep Learning Algorithms

Adluru, Abhiram (2024) Improving Cloud Security with Real-Time Detection of APT Attacks Using Advanced Deep Learning Algorithms. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Cloud environments are becoming increasingly susceptible to Advanced Persistent Threats (APTs), threatening both data security and systems reliability. Conventional detection methods such as signature- or rule-based systems are generally incapable of identifying behaviours of an evolved attack mechanism due to their static nature. a detection system has been proposed which handles APT attack with real-time capabilities using deep learning models-CNN, LSTM, and ConvLSTM-to identify malicious activities in network traffic. Our approach, unlike prior ones, recognizes spatiotemporal patterns through advanced feature engineering and balance of the datasets. The system is implemented as a scalable web application on AWS Elastic Beanstalk, enabling real-time monitoring with instant feedback with the help of a user-friendly interface. Evaluation results have highlighted ConvLSTM as being the most efficient among all models under consideration, having exhibited higher values of precision and recall, as well as greater stability.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas 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 > 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:	14 Jul 2025 13:57
Last Modified:	14 Jul 2025 13:57
URI:	https://norma.ncirl.ie/id/eprint/8078

Actions (login required)

View Item