Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 9

FEDERAL UNIVERSITY OF TECHNOLOGY,

OWERRI, P.M.B. 1526

A RESEARCH REPORT

ON

CYBER THREAT DETECTION SYSTEM USING A


HYBRID APPROACH OF TRANSFER LEARNING
IN NIGERIA TELECOMMUNICATION

PRESENTED TO

THE DEPARTMENT OF INFORMATION TECHNOLOGY


SCHOOL OF INFORMATION AND
COMMUNICATION TECHNOLOGY, SICT

BY

CYBER SECURITY STUDENTS


400 LEVEL

IN PARTIAL FULFILLMENT OF THE REQUIREMENT


FOR THE AWARD OF BACHELOR OF TECHNOLOGY
(B.TECH) IN CYBER SECURITY

SUBMISSION DATE: 1ST JULY, 2024


i
CONTRIBUTORS
S/N NAMES REG NO DEPARTMENT
1. OBINNA SHALOM CHIJINDU 20201214042 CYB (GROUP LEADER)
2. DAVIDS SYLVESTER CHINEDU 20212321242 MEMBER
3.
5.

ii
CERTIFICATION

This is to certified that this research work was carried out by the Group One of
CYBER SECURITY Students, 400 Level in SCHOOL OF INFORMATION AND
COMMUNICATION TECHNOLOGY, SICT of Federal University of Technology,
Owerri.

______________________ __________________
RESEARCH INSTRUCTOR GROUP LEADER

iii
DEDICATION

This research report is dedicated to God Almighty who has sustained and kept us
alive to this moment to research and document this report for future use and also to
our family members especially to our parents, who ensure that we don’t lack
anything at our stay in Futo.

iv
ACKNOWLEDGEMENT

We would like to express our sincere gratitude to all who have contributed to the
compilation of this report and making it a success (Cyber Security Students, 400
Level).

We will also like to thank the Dean and HODs of School of information and
Communication Technology for giving us the privilege to offer this course which
propels us to know how to write and present a reasonable report like this

Furthermore, we would express our sincere heartfelt gratitude to our Lecturer Engr
Tochukwu, whose guidance, tutelage, expertise and unwavering support were
instrumental in shaping the path of this research work. His corrections, feedbacks
and valuable suggestion played a vital role in shaping this report.

Also, I will like to thank the school authorities for aligning course like Csc 407, which
served as a guide to write a research paper, as the course gives a detailed guideline
on how to write a research paper.

v
ABSTRACT

This research addresses the growing concern of cyber threats in Nigeria's


telecommunications sector, a critical area given the rapid technological
advancements and increased digital connectivity. Traditional cyber threat detection
systems, while beneficial, often fall short in detecting the sophisticated and large-
scale attacks seen today. This study aims to develop and implement a hybrid cyber
threat detection system that combines traditional machine learning (ML) and transfer
learning (TL) approaches to improve the accuracy and efficiency of threat detection.

The primary goal of this research is to design and evaluate a hybrid model that
enhances cyber threat detection capabilities beyond what standalone models can
achieve. To accomplish this, we focused on three main objectives. First, we
developed a comprehensive dataset that integrates synthetic data with real-world
telecommunication data from Nigeria, providing a robust foundation for model
training and testing. Second, we implemented and optimized a hybrid detection
model that combines the strengths of traditional ML techniques with the advanced
capabilities of TL. Third, we conducted a comparative analysis to measure the
performance of the hybrid model against traditional ML and standalone TL models,
using metrics such as accuracy, precision, recall, and F1-score.

Our methodology involved an extensive literature review to identify the limitations of


existing cyber threat detection technologies. We used various datasets, including
NSL-KDD, UNSW-NB15, CICIDS2017, and real-world Nigerian telecommunication
data. These datasets were preprocessed to ensure they were suitable for model
training. The hybrid model was then trained and tested on these datasets, and its
performance was evaluated against the traditional ML and TL models.

The results were promising. The hybrid model outperformed both the traditional ML
and standalone TL models across all datasets. It achieved higher accuracy, precision,
recall, and F1-scores, demonstrating its ability to detect a wide range of cyber
threats more effectively. The hybrid approach showed particular strength in
identifying both known and unknown attacks, making it an ideal solution for the
dynamic and complex threat landscape in Nigeria's telecommunications sector.

The implications of this research are significant for policymakers, telecommunication


companies, and cybersecurity practitioners. It highlights the need for advanced,
hybrid approaches in cyber threat detection to keep up with the evolving nature of
cyber threats. The findings suggest that a combination of ML and TL techniques can
significantly enhance the performance of detection systems, providing a robust
defense against cyber-attacks.

This study showcases the effectiveness of a hybrid cyber threat detection system for
Nigeria's telecommunication sector. By leveraging the complementary strengths of
traditional ML and TL, the proposed system offers a robust and adaptable solution to
improve cybersecurity. Future research should focus on real-time implementation of
these models, further optimization, and continuous adaptation to new threats.

vi
Interdisciplinary collaboration and investment in cybersecurity infrastructure and
training will be crucial for sustaining the security of telecommunication networks in
Nigeria and beyond.

Keywords: Cyber Threat Detection, Hybrid Approach, Transfer Learning, Machine


Learning, Telecommunication Security, Nigeria, Network Intrusion Detection,
Cybersecurity, Telecommunication Networks, Advanced Threat Protection

vii
TABLE OF CONTENT

COVER PAGE ………………………………………………………………………….…………………….… I


CONTRIBUTORS ………………………………………………………………………….………………… II
CERTIFICATION …………………………………………………………..………………………………. III
DEDICATION ……………………………………………………………………………..………………… IV
ACKNOWLEDGEMENT ……………………………………………………………..………………….... V
ABSTRACT …………………………………………………………………………….……………… VI- VII
TABLE OF CONTENT …………………………………………….………………………………VIII - IX
CHAPTER ONE
1.0. Introduction
…………………………………………………………………………………………….
1.1. Background Of The Study …………………………………………………………………….
…..
1.2. Problem Statement ……………………………………………………………………………….
….
1.3. Purpose Of The Study …………………………………………………………………...…….
……
1.4. Research Questions …………………………………………………….………………………..…
1.5. Significance Of The Study ……………………………………………………….…………….…
1.6. Scope Of The Study ……………………………………………………………….……………….
1.7. Operational Definitions of Terms ……………………………………………………………..
1.7. Research Contribution ………………………………………………..……………………………
CHAPTER TWO
2.0 LITERATURE REVIEW …………………………………………………………………….………
2.1.0 CONCEPTUAL FRAMEWORK ……………………………………………………………………
2.1.1 Nigeria Telecommunication ……………………………………………………………
2.1.2 Cyber threats in telecommunication ………………………………………………..
2.1.3. Transfer learning and its applications ………………………………………………
2.1.4 Hybrid approaches for cyber threat detection …………………………………..

2.2.0 EMPIRICAL REVIEW


2.2.1. Cyber Threat Detection Based on Artificial Neural Networks
Using Event Profiles ………………………………………………………………….……
2.2.2. Transfer Learning and Domain Adaptation in Telecommunications ……..
2.2.3 Real-Time Content-Based Cyber Threat Detection with Machine
Learning ………………………………………………………………………………………
2.2.4. Transfer Learning: A New Promising Technique Cyber Security Threat
Detection Model Using Artificial Intelligence Techniques ……………………
2.2.5. A malware detection system using a hybrid approach of multi-heads
attention-based control flow traces and image visualization ………………
2.2.6. Cyber-Threat Detection System Using a Hybrid Approach of Transfer
Learning and Multi-Model Image Representation ………………………………
2.2.7. Hacking And Cyber Security In Nigeria Telecommunication Industry:
Implication For Teaching And Learning ……………………………………………

viii
2.3.0. RESEARCH GAPS TO FILL
2.3.1. Limited research on the application of transfer learning in cyber threat
detection in the Nigeria telecommunication sector …………………………….
2.3.2. Need for a comprehensive hybrid approach combining transfer learning
with other techniques for enhanced cyber threat detection ………………..

CHAPTER THREE
3.0. Methodology …………………………………………………………………………………..……
3.1. Research Design …………………………………………….…………………………….….…..
3.2. Material ……………………………..………………………………………………………………..
3.3. Method to Achieve Results ………………………………………………………………..
3.4. Instrument for Data Collection
3.5. Method for Data Collection ………………………………………………………………..
3.6. Data Analysis ………………………………………………………………………………………
CHAPTER FOUR
4.0. Results and Discussions ………………………………………………………………………….
4.1. Dataset Preparation ……………………………………………………………………………….
4.2. Result Analysis and Performance Comparison ……………………………….………….
CHAPTER FIVE
5.0 Conclusions …………………………………………………………………………………………
Recommendation …………………………………………………………………………….…………….
Appendix ………………………………………………………………………………….…………..………
Reference ………………………………………………………………………………….………………….

ix

You might also like