Final Year
Get Started
Preview only — this sample cannot be downloaded or printed.
Final YearPreview only

A project submitted to the Department of Cybersecurity

Design and Implementation of a Machine-Learning-Based Network Intrusion Detection System

By

Adaeze Okonkwo

U/2013/ABC/0186

In partial fulfilment of the requirements for the award of a Bachelor's degree

Supervisor: Prof. D. C. Umeh

2023

Abstract

This project builds a network intrusion detection system (NIDS) that classifies network traffic as benign or attack using machine learning. The model is trained on NSL-KDD/CICIDS and exposed via a dashboard that flags suspicious packets in near real-time. The study is organised into five chapters covering the introduction, review of related literature, system analysis and design, implementation and testing, and the summary, conclusion and recommendations.

Table of Contents

Chapter One: Introduction

  1. 1.1 Background to the Study4
  2. 1.2 Statement of the Problem6
  3. 1.3 Aim and Objectives of the Study8
  4. 1.4 Research Questions10
  5. 1.5 Significance of the Study12
  6. 1.6 Scope of the Study14
  7. 1.7 Limitations of the Study16
  8. 1.8 Operational Definition of Terms18

Chapter Two: Literature Review

  1. 2.1 Conceptual Review16
  2. 2.2 Theoretical Framework18
  3. 2.3 Empirical Review of Related Studies20
  4. 2.4 Gap in Literature22
  5. 2.5 Summary of Literature Review24

Chapter Three: System Analysis and Design

  1. 3.1 Analysis of the Existing System28
  2. 3.2 Problems of the Existing System30
  3. 3.3 Proposed System32
  4. 3.4 System Requirements Specification34
  5. 3.5 System Design and Architecture36
  6. 3.6 Database Design38
  7. 3.7 Use Case and Flow Diagrams40

Chapter Four: Implementation and Testing

  1. 4.1 System Implementation40
  2. 4.2 Choice of Development Tools42
  3. 4.3 System Testing44
  4. 4.4 Test Results and Evaluation46
  5. 4.5 System Documentation48

Chapter Five: Summary, Conclusion and Recommendations

  1. 5.1 Summary of Findings52
  2. 5.2 Conclusion54
  3. 5.3 Recommendations56
  4. 5.4 Suggestions for Further Studies58

References

Appendices

Final YearPreview only

Chapter One: Introduction

1.1 Background to the Study

This project builds a network intrusion detection system (NIDS) that classifies network traffic as benign or attack using machine learning. The model is trained on NSL-KDD/CICIDS and exposed via a dashboard that flags suspicious packets in near real-time.

1.2 Statement of the Problem

Network intrusion detection system using machine learning on the NSL-KDD or CICIDS dataset. Existing approaches remain limited in reach, accuracy and ease of use, which creates the gap this study addresses.

1.3 Aim and Objectives

The aim of this study is to deliver a machine-learning-based network intrusion detection system. The specific objectives are to:

  1. review existing literature and systems related to the study;
  2. design and build the system using Python, scikit-learn, Wireshark;
  3. evaluate the results against the stated problem;
  4. make recommendations for practice and further research.

1.4 Scope of the Study

Introduction: background to ML-based intrusion detection, statement of the problem (Nigerian SMEs lack affordable cybersecurity tools and suffer rising attacks), aim and objectives, research questions, scope, significance of the study, and definition of terms.

Chapter Two: Literature Review

Literature Review: theoretical framework, review of related works on ML-based intrusion detection, gaps in existing studies, and a summary positioning this project. Literature Review: theoretical framework, review of related works on ML-based intrusion detection, gaps in existing studies, and a summary positioning this project.

Chapters 2–5 are not part of this preview.