Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Analysis and Prediction of Cyber-Threat Fragments in Banking Critical Infrastructure Sector

Kebande, Victor and Nguyen, Vinh LU (2024) DABN01 20241
Department of Economics
Department of Statistics
Abstract
Continued digitization has seen the banking sector which is positioned as a national critical infrastructure face an ever-growing number of cyber-threats. This, has necessitated the need for proactive measures for detection and prevention, owing to an expanded threat landscape. This thesis proposes an approach centered on leveraging data analysis and Machine Learning (ML) to analyze and predict the existence of potential cyber-threat fragments (CF) within the Banking Critical Infrastructure (BCI). By harnessing the power of advanced analytics techniques, and predictive modeling, the study aims to uncover hidden insights from historical cyber-threat data. This study has leveraged Microsoft Malware Prediction Dataset that has been curated by... (More)
Continued digitization has seen the banking sector which is positioned as a national critical infrastructure face an ever-growing number of cyber-threats. This, has necessitated the need for proactive measures for detection and prevention, owing to an expanded threat landscape. This thesis proposes an approach centered on leveraging data analysis and Machine Learning (ML) to analyze and predict the existence of potential cyber-threat fragments (CF) within the Banking Critical Infrastructure (BCI). By harnessing the power of advanced analytics techniques, and predictive modeling, the study aims to uncover hidden insights from historical cyber-threat data. This study has leveraged Microsoft Malware Prediction Dataset that has been curated by Microsoft for the purpose of advancing research in malware detection and prediction using ML classification models and Deep learning approach. We then evaluate and compare the effectiveness of several classifiers, including Random Forest (RF), Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), XGBoost, and a Fully Connected Neural Network (FCNN). RF achieved an accuracy of 61.7%, LR 60.6%, QDA model achieved an accuracy of 57.15%, LDA 60.45%, XGBoost 61.25% and FCNN 52.35% respectively. From these results, it is evident that Ensemble methods like Random Forest and gradient boosting techniques like XGBoost outperformed other models in terms of accuracy and other evaluation metrics. LR and LDA also demonstrated competitive performance. These findings suggest that Ensemble methods and Gradient boosting techniques are promising approaches for cyber threat detection tasks in banking infrastructures. (Less)
Please use this url to cite or link to this publication:
author
Kebande, Victor and Nguyen, Vinh LU
supervisor
organization
course
DABN01 20241
year
type
H1 - Master's Degree (One Year)
subject
keywords
Analysis, prediction, cyber-threats, banking, critical infrastructure
language
English
id
9174244
date added to LUP
2024-09-24 08:33:19
date last changed
2025-04-01 08:44:12
@misc{9174244,
  abstract     = {{Continued digitization has seen the banking sector which is positioned as a national critical infrastructure face an ever-growing number of cyber-threats. This, has necessitated the need for proactive measures for detection and prevention, owing to an expanded threat landscape. This thesis proposes an approach centered on leveraging data analysis and Machine Learning (ML) to analyze and predict the existence of potential cyber-threat fragments (CF) within the Banking Critical Infrastructure (BCI). By harnessing the power of advanced analytics techniques, and predictive modeling, the study aims to uncover hidden insights from historical cyber-threat data. This study has leveraged Microsoft Malware Prediction Dataset that has been curated by Microsoft for the purpose of advancing research in malware detection and prediction using ML classification models and Deep learning approach. We then evaluate and compare the effectiveness of several classifiers, including Random Forest (RF), Logistic Regression (LR), Quadratic Discriminant Analysis (QDA), Linear Discriminant Analysis (LDA), XGBoost, and a Fully Connected Neural Network (FCNN). RF achieved an accuracy of 61.7%, LR 60.6%, QDA model achieved an accuracy of 57.15%, LDA 60.45%, XGBoost 61.25% and FCNN 52.35% respectively. From these results, it is evident that Ensemble methods like Random Forest and gradient boosting techniques like XGBoost outperformed other models in terms of accuracy and other evaluation metrics. LR and LDA also demonstrated competitive performance. These findings suggest that Ensemble methods and Gradient boosting techniques are promising approaches for cyber threat detection tasks in banking infrastructures.}},
  author       = {{Kebande, Victor and Nguyen, Vinh}},
  language     = {{eng}},
  note         = {{Student Paper}},
  title        = {{Analysis and Prediction of Cyber-Threat Fragments in Banking Critical Infrastructure Sector}},
  year         = {{2024}},
}