Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector
Thesis (MA)--Stellenbosch University, 2025.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Stellenbosch : Stellenbosch University
2026
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613898688954368 |
|---|---|
| access_status_str | Open Access |
| author | Mulea, Prince Rotondwa |
| author2 | Blaauw, D. N. |
| author_browse | Blaauw, D. N. Mulea, Prince Rotondwa |
| author_facet | Blaauw, D. N. Mulea, Prince Rotondwa |
| author_sort | Mulea, Prince Rotondwa |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MA)--Stellenbosch University, 2025. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/134727 |
| institution | Stellenbosch University (South Africa) |
| language | English |
| last_indexed | 2026-06-10T12:43:27.297Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2026 |
| publishDateRange | 2026 |
| publishDateSort | 2026 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/134727 AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector Mulea, Prince Rotondwa Blaauw, D. N. Stellenbosch University. Faculty of Arts and Social Sciences. Dept. of Information Science. Financial institutions -- Computer networks -- Security measures Electronic banking -- Security measures Internet banking -- Security measures Intrusion detection systems (Computer security) Cybersecurity Financial services industry -- Technological innovations UCTD Thesis (MA)--Stellenbosch University, 2025. Mulea, P. R. 2025. AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the Banking Sector. Unpublished masters thesis. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/5e8c0d17-0321-4724-91da-bfcad35cee30 ENGLISH SUMMARY: The digital transformation of the financial services sector, accelerated by the emergence of neobanks and advanced online platforms, has markedly increased its exposure to sophisticated cyberthreats. High-profile incidents, such as coordinated attacks on financial institutions in Iraq, have demonstrated the severe operational, economic, and reputational consequences that can arise from delayed threat detection and inadequate mitigation. Traditional cybersecurity measures, including firewalls, antivirus software, and signature-based intrusion detection systems, remain constrained by their dependence on known attack signatures, thereby leaving financial networks susceptible to zero-day exploits, AI-driven intrusions, and complex multi-vector threats. This study proposes and evaluates a supervised machine learning intrusion detection and prevention model aimed at proactively securing financial networks. To simulate realistic network conditions and generate representative traffic data, a banking environment was constructed using GNS3. To address class imbalance within the dataset, the Synthetic Minority Oversampling Technique (SMOTE) was employed, thereby improving the detection of minority-class attack instances. Several machine learning algorithms, including Support Vector Machine (SVM), Multi-Layer Perceptron Neural Network (MLPNN), and Long Short-Term Memory (LSTM), were assessed using key performance metrics to determine their effectiveness. The Decision Tree model demonstrated superior performance, achieving an accuracy rate of 99.98%, perfect precision and recall, zero false positives, and only thirteen false negatives. These results underscore its capacity to deliver highly accurate, real-time threat detection while minimising operational disruptions caused by false alarms. Additionally, its transparent decision-making process enhances explainability, supports regulatory compliance, and fosters institutional trust, factors that are critical in the context of financial cybersecurity. The findings validate the viability of interpretable, high-performance machine learning models for the real-time detection and mitigation of advanced cyberthreats, including Distributed Denial-of-Service (DDoS) attack patterns. Future research should prioritise scaling the simulation framework to encompass more complex financial network topologies, integrating adaptive online learning capabilities, and incorporating explainable artificial intelligence (XAI) techniques to enhance resilience against emerging attack vectors. AFRIKAANSE OPSOMMING: Die digitale transformasie van die finansieledienstesektor, versnel deur die opkoms van neobanke en gevorderde aanlynplatforms, het die blootstelling daarvan aan gesofistikeerde kuberbedreigings aansienlik verhoog. Hoeprofielvoorvalle, soos gekoordineerde aanvalle op finansiele instellings in Irak, het die ernstige operasionele, ekonomiese en reputasiegevolge gedemonstreer wat kan voortspruit uit vertraagde bedreigingsopsporing en onvoldoende versagting. Tradisionele kuberveiligheidsmaatreels, insluitend (vuurmure) firewalls, antivirusprogrammatuur en handtekening-gebaseerde indringingsopsporingstelsels, bly beperk deur hul afhanklikheid van bekende aanvalshandtekeninge, waardeur finansiele netwerke vatbaar is vir nul-dag-uitbuiting, KI-gedrewe indringings en komplekse multi-vektor-bedreigings. Hierdie studie stel 'n toesighouerde masjienleer-indringingsopsporings- en voorkomingsmodel voor wat daarop gemik is om finansiele netwerke proaktief te beveilig. Om realistiese netwerktoestande te simuleer en verteenwoordigende verkeersdata te genereer, is 'n bankomgewing met behulp van GNS3 gebou. Om klaswanbalans binne die datastel aan te spreek, is die Sintetiese Minderheidsoorsteekproefnemingstegniek (SMOTE) gebruik, wat die opsporing van minderheidsklas-aanvalgevalle verbeter het. Verskeie masjienleer-algoritmes, insluitend Support Vector Machine (SVM), Multi-Layer Perceptron Neural Network (MLPNN), en Long Short-Term Memory (LSTM), is geassesseer met behulp van sleutelprestasiemaatstawwe om hul doeltreffendheid te bepaal. Die Besluitboom-model het uitstekende prestasie getoon, met 'n akkuraatheidskoers van 99.98%, perfekte presisie en herroeping, nul vals positiewe en slegs dertien vals negatiewe. Hierdie resultate beklemtoon die vermoe om hoogs akkurate, intydse bedreigingsopsporing te lewer, terwyl operasionele ontwrigtings wat deur vals alarms veroorsaak word, tot die minimum beperk word. Daarbenewens verbeter die deursigtige besluitnemingsproses die verduidelikbaarheid, ondersteun dit regulatoriese voldoening en bevorder dit institusionele vertroue, faktore wat krities is in die konteks van finansiele kuberveiligheid. Die bevindinge bevestig die lewensvatbaarheid van interpreteerbare, hoeprestasie-masjienleermodelle vir die intydse opsporing en versagting van gevorderde kuberbedreigings, insluitend verspreide Denial-of-Service (DDoS)-aanvalpatrone. Toekomstige navorsing behoort die skalering van die simulasieraamwerk te prioritiseer om meer komplekse finansiele netwerktopologiee in te sluit, aanpasbare aanlyn leervermoens te integreer en verduidelikbare kunsmatige intelligensie (XAI)-tegnieke in te sluit om veerkragtigheid teen opkomende aanvalvektore te verbeter. Masters 2026-01-05T12:41:54Z 2026-01-05T12:41:54Z 2025-12 Thesis https://scholar.sun.ac.za/handle/10019.1/134727 en Stellenbosch University xix, 173 pages : illustrations, maps, includes annexures application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Financial institutions -- Computer networks -- Security measures Electronic banking -- Security measures Internet banking -- Security measures Intrusion detection systems (Computer security) Cybersecurity Financial services industry -- Technological innovations UCTD Mulea, Prince Rotondwa AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title | AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title_full | AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title_fullStr | AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title_full_unstemmed | AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title_short | AI-Augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| title_sort | ai augmented proactive cyber detection and mitigation of cybersecurity threats in the banking sector |
| topic | Financial institutions -- Computer networks -- Security measures Electronic banking -- Security measures Internet banking -- Security measures Intrusion detection systems (Computer security) Cybersecurity Financial services industry -- Technological innovations UCTD |
| url | https://scholar.sun.ac.za/handle/10019.1/134727 |
| work_keys_str_mv | AT muleaprincerotondwa aiaugmentedproactivecyberdetectionandmitigationofcybersecuritythreatsinthebankingsector |