A Comparative Analysis of Hybrid Machine Learning Techniques for Network Intrusion Detection in Cloud Environments - MSc Research Project

Sep 17, 2026

Uploaded by Levi

Network Intrusion Detection Systems (NIDS) in cloud environments are examined through the use and comparison of machine learning algorithms. With cyber threats increasing rapidly, traditional signature-based NIDS are less effective against advanced attacks such as polymorphic malware and zero-day exploits. The study proposes a hybrid NIDS combining Random Forest classifiers and Long Short-Term Memory (LSTM) networks. Using the UNSW-NB15 dataset, the research aims to deliver a robust, highly accurate detection model for defending cloud stakeholders against evolving threats.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Introduction

Cloud computing context and security challenges

Limitations of signature-based NIDS against modern threats

Motivation for advanced, adaptive NIDS using machine learning

A Comparative Analysis of Hybrid Machine Learning Techniques for Network Intrusion Detection in Cloud Environments. MSc Research Project MSc Cloud Computing Prajesh Nikhil Rajendrasubbu Student ID: 22233784 School of Computing National College of Ireland Supervisor: Aqeel Kazmi National College of Ireland MSc Project Submission Sheet School of Computing Student Name: PRAJESH NIKHIL RAJENDRASUBBU Student ID: X22233784 Programme: MSCCLOUD Year: 2023-2024 Module: MSCCLOUD Research Project Supervisor: Aqeel Kazmi Submission Due Date: 12/08/2024 Project Title: A Comparative Analysis of Hybrid Machine Learning Techniques for Network Intrusion Detection in Cloud Environments. Word Count: 8700 Page Count: 22 I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author's written or electronic work is illegal (plagiarism) and may result in disciplinary action. Signature: PRAJESH NIKHIL RAJENDRASUBBU Date: 12/08/2024 PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST | Attach a completed copy of this sheet to each project (including multiple copies) | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both for your own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator Office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | | Penalty Applied (if applicable): | | A Comparative Analysis of Hybrid Machine Learning Techniques for Network Intrusion Detection in Cloud Environments. Prajesh Nikhil Rajendrasubbu 22233784 Abstract Network Intrusion Detection Systems (NIDS) within cloud environments by using and comparing machine learning algorithms. Due to the increasing number of cyber threats, there is a need to safeguard critical data in cloud environments. The existing methods such as NIDS, in particular traditional signature-based NIDS, are becoming less and less effective against advanced threats like polymorphic malware and zero-day attacks. Previous work raised attention to the problems of these conventional strategies and suggested replacements such as advanced machine learning methods and anomaly-based detection. By developing a hybrid NIDS model that combines Random Forest (RF) classifiersand Long Short-Term Memory (LSTM) networks, this study fills in these gaps. this study explores the diverse machine learning technologies using deep learning to determine an efficient and highly accurate model to detect intruders in cloud environments. The goal of this research is to develop a strong and effective network intrusion detection system (NIDS) that can navigate the intricacies of cloud environments and offer superior defence against cyber threats by utilizing the extensive UNSW-NB15 dataset. The main goal is to develop an advanced NIDS model capable of navigating cloud complexities and give a valuable enhanced model to stakeholders to help defend against cyber threats by achieving high accuracy using hybrid models and with comparison with the other Machine learning model which can lead to the development of more robust NIDS in cloud environments. 1 Introduction Cloud Computing has a distributed software architecture the primary aim of cloud computing is to provide worldwide access to the internet for the users. In recent

FAQs

What is the main objective of this MSc research project?

To develop and evaluate a network intrusion detection system for cloud environments using a hybrid approach and comparison with other machine learning models.

Why are traditional signature-based NIDS methods considered less effective?

They struggle to detect novel and advanced attacks such as zero-day exploits and polymorphic malware, which require more adaptive techniques.

Which hybrid machine learning methods does the study use?

It combines Random Forest (RF) classifiers with Long Short-Term Memory (LSTM) networks in a hybrid NIDS model.

Sep 17, 2026

Uploaded by Levi