DECISION-AWARE AI FRAUD PREVENTION IN DIGITAL BANKING

Abdulaziz O. Ibiyeye; Tawakalit O. Ibiyeye

doi:10.5281/zenodo.21271639

Abstract

Artificial intelligence is now embedded in mainstream fraud controls across digital banking, payment apps, and
fintech platforms. Yet the most difficult scams increasingly do not look like classic account takeover. In many
modern scam events, the legitimate customer logs in with their own credentials, passes multi-factor authentication,
and approves the payment while under deception, pressure, false urgency, impersonation, or other forms of social
engineering. That is the central challenge of authorized push payment (APP) fraud and related customerauthorized scams: the bank may see a real customer and a technically valid payment even though the decision
itself is compromised (Braithwaite, 2024; Federal Reserve Bank of Atlanta, 2024).
This white paper argues that banks need to move beyond a narrow “AI detects fraud” posture and adopt a decisionaware fraud prevention framework. Traditional models remain necessary, but they are structurally strongest when
fraud resembles stolen credentials, suspicious devices, anomalous geolocations, abnormal transaction values, or
known fraud patterns. They are much weaker when the risk resides in the decision context: the customer is real,
the authentication succeeds, and the payment appears procedurally normal, but the customer has been manipulated
into acting against their own interest. FFIEC guidance is already compatible with this view because it emphasizes
risk-based authentication, layered security, transaction risk, monitoring, customer education, and controls
responsive to faster payments and push-payment capabilities (Federal Financial Institutions Examination Council
[FFIEC], 2021).
Recent public evidence underscores the urgency. UK Finance reported that criminals stole £1.17 billion through
authorized and unauthorized fraud in 2024; banks prevented £1.45 billion of unauthorized fraud, but APP fraud
still caused £450.7 million in losses, with 70% of APP cases beginning on online platforms and 16% on
telecommunications networks. In the United States, the FTC reported $12.5 billion in fraud losses in 2024,
including $2.95 billion in imposter-scam losses, with consumers losing more through bank transfers or
cryptocurrency than through all other payment methods combined (Federal Trade Commission [FTC], 2025; UK
Finance, 2025).

Keywords

Not provided

References

1) Ali, A., Abd Razak, S., Othman, S. H., Eisa, T. A. E., Al-Dhaqm, A., Nasser, M., Elhassan, T., Elshafie,
H., & Saif, A. (2022). Financial fraud detection based on machine learning: A systematic literature
review. Applied Sciences, 12(19), 9637. https://doi.org/10.3390/app12199637
2) Baig, A. F., Eskeland, S., & Yang, B. (2023). Privacy-preserving continuous authentication using
behavioral biometrics. International Journal of Information Security, 22, 1833–1847.
https://doi.org/10.1007/s10207-023-00721-y
3) Braithwaite, J. (2024). Authorized push payment bank fraud: What does an effective regulatory response
look like? Journal of Financial Regulation, 10(2), 174–193. https://doi.org/10.1093/jfr/fjae006
4) Boulieris, P., Pavlopoulos, J., Xenos, A., Artman, V., & Vassalos, V. (2024). Fraud detection with natural
language processing. Machine Learning, 113, 5087–5108. https://doi.org/10.1007/s10994-023-06354-5
5) Černevičienė, J., & Kabašinskas, A. (2024). Explainable artificial intelligence in finance: A systematic
literature review. Artificial Intelligence Review, 57, Article 216. https://doi.org/10.1007/s10462-024-
10854-8
6) Daiku, Y., Kugihara, N., Teraguchi, T., & Watamura, E. (2020). Effective forewarning requires central
route processing: Theoretical improvements on the counterargumentation hypothesis and practical
implications for scam prevention. PLOS ONE, 15(3), e0229833.
https://doi.org/10.1371/journal.pone.0229833
7) Dopamu, O., Adesiyan, J., & Oke, F. (2024). Artificial intelligence and U.S. financial institutions:
Review of AI-assisted regulatory compliance for cybersecurity. World Journal of Advanced Research
and Reviews, 21(3), 964–979. https://doi.org/10.30574/wjarr.2024.21.3.0791
8) Federal Financial Institutions Examination Council. (2021). Authentication and access to financial
institution services and systems. https://www.ffiec.gov/sites/default/files/media/pressreleases/2021/authentication-and-access-to-financial-institution-services-and-systems.pdf
9) Federal Reserve Bank of Atlanta. (2024). Addressing authorized push payment scams in the U.S.
https://www.atlantafed.org/research-and-data/publications/take-on-payments/2024/09/23/addressingauthorized-push-payment-fraud-in-us
10) Federal Trade Commission. (2025). New FTC data show a big jump in reported losses to fraud to $12.5
billion in 2024. https://www.ftc.gov/news-events/news/press-releases/2025/03/new-ftc-data-show-bigjump-reported-losses-fraud-125-billion-2024
11) Finnegan, O. L., White, J. W., Armstrong, B., Adams, E. L., Burkart, S., Beets, M. W., Nelakuditi, S.,
Willis, E. A., von Klinggraeff, L., Parker, H., Bastyr, M., Zhu, X., Zhong, Z., & Weaver, R. G. (2024).
The utility of behavioral biometrics in user authentication and demographic characteristic detection: A
scoping review. Systematic Reviews, 13, Article 61. https://doi.org/10.1186/s13643-024-02451-1
12) Ibiyeye, T. O., Iornenge, A., Terdoo, J., & Adegibite, A. (2024). Evaluating regulatory compliance in the
finance and investment sector: An analysis of current practices, challenges, and the impact of emerging
technologies. IOSR Journal of Economics and Finance (IOSR-JEF), 15(6, Series 1).
13) Ibiyeye, A., Ibiyeye, T. O., & Oke, F. (2025). RegTech readiness for financial institut ions in the AI
governance era: Emerging technology risk, internal control, and inclusive compliance modernization.
World Journal of Advanced Research and Reviews, 27(2), 2249–2264.
https://doi.org/10.30574/wjarr.2025.27.2.3522
14) Ibiyeye, T. O., Oke, F., Wijetunge, M., & Ibiyeye, A. (2026). The RegTech Compliance Automation
Framework (RCAF): An AI-enabled governance architecture for financial institutions, community
banks, and underserved markets. International Journal of Engineering Technology Research &
Management, 10(6), 267–277. https://doi.org/10.5281/zenodo.20721044
15) National Institute of Standards and Technology. (2023). Artificial intelligence risk management
framework (AI RMF 1.0) (NIST AI 100-1). U.S. Department of Commerce.
https://doi.org/10.6028/NIST.AI.100-1
16) Oke, F., Oyeneye, B., Umakor, M. F., & Dopamu, O. (2025). Designing a real-time, AI-driven
communication layer for fraud detection in financial services. IOSR Journal of Computer Engineering,
27(4), 32–45. https://doi.org/10.9790/0661-2704033245
17) Okolie, A., Oibiyeye, S., Ibiyeye, A. O., & Olukoya, D. (2026). A risk-based security governance
framework for modern information systems. Journal of Computational Analysis and Applications
(JoCAAA), 35(1), 475–488. https://eudoxuspress.com/index.php/pub/article/view/4733
18) Onwuegbuchi, O., Ibiyeye, A. O., Okolo, J. N., & Adeniji, S. A. (2023). Cybersecurity risks in the fintech
ecosystem: Regulatory and technological perspectives. Communication in Physical Sciences, 9(4), 947–
967. https://journalcps.com/index.php/volumes/article/view/723
19) Schmitt, M., & Flechais, I. (2024). Digital deception: Generative artificial intelligence in social
engineering and phishing. Artificial Intelligence Review, 57, Article 324.
https://doi.org/10.1007/s10462-024-10973-2
20) Talukder, M. A., Khalid, M., & Uddin, M. A. (2024). An integrated multistage ensemble machine
learning model for fraudulent transaction detection. Journal of Big Data, 11, Article 168.
https://doi.org/10.1186/s40537-024-00996-5
21) Teichmann, F. M. J., & Falker, M.-C. (2023). Online payment fraud: From anomaly detection to risk
management. Financial Innovation, 9, Article 66. https://doi.org/10.1186/s40854-023-00470-w
22) UK Finance. (2025). Fraud continues to pose a major threat with over £1 billion stolen in 2024.
https://www.ukfinance.org.uk/news-and-insight/press-release/fraud-report-2025-press-release
23) Xu, D., Murphy, L., & Chen, T. (2024). Falling for tourist scams: An examination of scam compliance
factors. Journal of Travel Research, 63(8), 1953–1970. https://doi.org/10.1177/00472875231206542
24) Zioviris, G., Kolomvatsos, K., & Stamoulis, G. (2024). An intelligent sequential fraud detection model
based on deep learning. The Journal of Supercomputing, 80, 14824–14847.
https://doi.org/10.1007/s11227-024-06030-y