Abstract

FinTech and the digital transformation of banking systems have redefined the banking industry, improving access to transactions and efficiency, and enhancing the customer experience. However, this transformation also exposes individuals and institutions to advanced cybersecurity threats, including phishing, malware, identity theft, insider attacks, and fraudulent financial transactions. Current security solutions are often inadequate in accommodating changing attack trends and the complexity of digital financial systems. This paper investigates the principal cybersecurity threats to digital banking systems and assesses existing fraud detection and prevention strategies. A systematic literature review of recent cybersecurity and financial technology publications is conducted, identifying the most critical vulnerabilities and weaknesses in existing financial security infrastructure. Drawing on the analysis, an integrated framework for fraud detection and prevention is proposed, combining AI-powered analytics, behavioral monitoring, multi-factor authentication, real-time transaction monitoring, and adaptive threat responses. The machine-learning detection layer of the framework is then evaluated empirically across three scenarios constructed from two public benchmark datasets: highly imbalanced credit card transaction fraud (284,807 transactions), network intrusion detection on the official NSL-KDD test split, and generalization to previously unseen attack patterns on the KDDTest-21 subset. Six detection models are compared using precision, recall, F1-score, ROC AUC, and precision-recall AUC. Ensemble methods perform strongest, with Random Forest reaching an F1-score of 0.8157 on transaction fraud with a false-positive rate of approximately 0.004%, and Gradient Boosting reaching a ROC AUC of 0.9610 on network intrusion; all models degrade markedly on unseen attack behavior, empirically supporting the adaptive retraining loop at the core of the proposed framework. Overall, this study contributes a practical, scalable, and empirically grounded framework that can help financial institutions improve cybersecurity governance and reduce the risk of financial loss from cybersecurity incidents.

References

• Hazar, A. and Babuşcu, Ş. 2023. Financial technologies: digital payment systems and digital banking. Today's dynamics. Journal of Research, Innovation and Technologies 2, 2, 162–178. https://doi.org/10.57017/jorit.v2.2(4).04
• Kizi, B. A. Q. 2025. Digital banking systems. Journal of Management and Economics 5, 6, 33–35. https://doi.org/10.55640/jme-05-06-07
• Tashtamirov, M. 2023. Financial innovation and digital technology in the banking system: an institutional perspective. SHS Web of Conferences 172, 02004. https://doi.org/10.1051/shsconf/202317202004
• Kagalwala, H. 2025. AI-powered FinTech: revolutionizing digital banking and payment systems. Journal of Information Systems Engineering and Management 10, 33s, 258–265. https://doi.org/10.52783/jisem.v10i33s.5475
• Paul, E. O., Callistus, O., Somtobe, O., Esther, T., Somto, K.-A., Clement, O., and Ejimofor, I. 2023. Cybersecurity strategies for safeguarding customers' data and preventing financial fraud in the United States financial sectors. International Journal on Soft Computing 14, 3, 1–16. https://doi.org/10.5121/ijsc.2023.14301
• Siddiqui, N. A. 2025. Assessing the influence of cybersecurity threats and risks on the adoption and growth of digital banking: a systematic literature review. American Journal of Advanced Technology and Engineering Solutions 1, 1, 226–257. https://doi.org/10.63125/fh49gz18
• Vuong, G. T. H., Barky, W., and Nguyen, M. H. 2025. Stabilizing the national banking system through digital financial inclusion, creative innovations, and green finance in low-financially developed economies. Journal of Open Innovation: Technology, Market, and Complexity 11, 1, 100434. https://doi.org/10.1016/j.joitmc.2024.100434
• Kasri, R. A., Indrastomo, B. S., Hendranastiti, N. D., and Prasetyo, M. B. 2022. Digital payment and banking stability in an emerging economy with a dual banking system. Heliyon 8, 11, e11198. https://doi.org/10.1016/j.heliyon.2022.e11198
• Ijiga, O. M., Idoko, I. P., Ebiega, G. I., Olajide, F. I., Olatunde, T. I., and Ukaegbu, C. 2024. Harnessing adversarial machine learning for advanced threat detection: AI-driven strategies in cybersecurity risk assessment and fraud prevention. Open Access Research Journal of Science and Technology 11, 1, 001–004. https://doi.org/10.53022/oarjst.2024.11.1.0060
• Ehsan, S. B., Saquib, Md. N., and Kakon, A. M. 2025. Blockchain-based cybersecurity solutions for secure financial transactions in digital banking systems. International Journal of Computer Applications 186, 59, 6–15. https://doi.org/10.5120/ijca2024924247
• Sitorus, R. S. and Hutagaol, B. J. 2025. Designing a zero trust architecture for securing API gateways in digital banking systems. Journal of Information Systems and Informatics 7, 3, 2589–2601. https://doi.org/10.51519/journalisi.v7i3.1219
• Sugiharto, B., Harkim, Simanungkalit, R. V., Siregar, I., and Andriani, M. 2023. Artificial intelligence (AI) architecture for an integrated smart digital banking system. Jurnal Penelitian Pendidikan IPA 9, 10, 876–882. https://doi.org/10.29303/jppipa.v9i10.4645
• Shoetan, P. O., Oyewole, A. T., Okoye, C. C., and Ofodile, O. C. 2024. Reviewing the role of big data analytics in financial fraud detection. Finance & Accounting Research Journal 6, 3, 384–394. https://doi.org/10.51594/farj.v6i3.899
• Metibemu, O. C. 2025. Financial risk management in digital-only banks: addressing fraud and cybersecurity threats in a cashless economy. Asian Journal of Research in Computer Science 18, 3, 434–455. https://doi.org/10.9734/ajrcos/2025/v18i3603
• Patel, K., Kashyap, S., and Agrawal, R. P. 2024. Footprints of FinTech on financial inclusion – evidence from digital banking system. International Education and Research Journal 10, 2. https://doi.org/10.21276/ierj24737981092606
• Mittapelly, A. K. 2023. AI-powered cybersecurity in Salesforce: strengthening fraud detection and risk management. International Journal of Innovative Research in Computer and Communication Engineering 11, 6. https://doi.org/10.15680/ijircce.2023.1106004
• Tan, H. 2025. Studies on the application and practice of artificial intelligence technology in e-commerce platform risk management. International Journal of Finance and Investment 2, 2, 20–24. https://doi.org/10.54097/q4nbzr57
• Kokogho, E., Odio, P. E., Ogunsola, O. Y., and Nwaozomudoh, M. O. 2025. A cybersecurity framework for fraud detection in financial systems using AI and microservices. Gulf Journal of Advance Business Research 3, 2, 410–424. https://doi.org/10.51594/gjabr.v3i2.90
• Abu-Dabaseh, F., Khtatbeh, M. M., Al'ararah, K., and Alassuli, A. 2025. Exploring the role of digital transformation in mitigating accounting fraud: a cybersecurity perspective. International Review of Management and Marketing 15, 3, 398–405. https://doi.org/10.32479/irmm.18490
• Tavallaee, M., Bagheri, E., Lu, W., and Ghorbani, A. A. 2009. A detailed analysis of the KDD CUP 99 data set. In Proceedings of the IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA 2009), 1–6. https://doi.org/10.1109/CISDA.2009.5356528
• Dal Pozzolo, A., Caelen, O., Johnson, R. A., and Bontempi, G. 2015. Calibrating probability with undersampling for unbalanced classification. In Proceedings of the IEEE Symposium Series on Computational Intelligence (SSCI 2015), 159–166. https://doi.org/10.1109/SSCI.2015.33.
• Pedregosa, F., Varoquaux, G., Gramfort, A., et al. 2011. Scikit-learn: machine learning in Python. Journal of Machine Learning Research 12, 2825–2830.