Adversarial and Dynamic Risk Management Framework: An Authorized Push Payment Fraud in the Generative AI Era

Adetunji Oludele Adebayo1, Uju Judith Eziokwu2, Omowunmi Folashayo Makinde3, & Olatunde Ayomide Olasehan4
1Information Security Manager / Independent researcher, University of Bradford
2Data Analyst/Independent Researcher, University of Bradford
3IT Support Engineer I/ Independent Researcher, University of the Cumberlands
4IT Engineer/Independent Researcher, Swansea University, UK
DOI – http://doi.org/10.37502/IJSMR.2025.81205

Abstract

The current reactive, liability-focused approach to managing Authorized Push Payment (APP) fraud is fundamentally insufficient against the sophisticated, rapidly evolving threats enabled by generative AI. This study addresses the dangerous asymmetry where criminals weaponize deepfake technologies and large language models for hyper-personalized social engineering, while existing defenses suffer from the “waterbed effect”. Annual losses from APP fraud exceed £1.1 billion in the UK and €4.3 billion across the EEA, yet current measures, like the UK’s mandatory reimbursement scheme and the EU’s Strong Customer Authentication, merely displace fraud to less regulated channels or shift tactics to authorized social engineering scams.

We propose the Adversarial and Dynamic Risk Management (ADRM) framework, a proactive model integrating Generative Adversarial Networks (GANs), ensemble machine learning, and Explainable AI (XAI). Using a synthetic dataset of 30,000 transactions, the analysis revealed that static safeguards are routinely bypassed, with 80.8% of fraudulent payments passing Confirmation of Payee (CoP) checks. Furthermore, vulnerable customers experienced a fraud rate 47% higher than the general population. The ADRM framework is projected to achieve a 70-90% reduction in undetected APP fraud by continuously adapting to adversarial scenarios and targeting root causes rather than post-event remediation. This research mandates a regulatory phase shift from liability allocation to proactive, predictive defense standards.

Keywords: Authorised Push Payment (APP) Fraud, Generative AI, Adversarial Risk Management (ADRM), Financial Crime, Deepfake, Explainable AI (XAI), Machine Learning, Social Engineering

References

  • Ali, A., Abd Razak, S., Othman, S. H., Eisa, T. A., 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
  • Bisht, U. & Pooja. (2025). Evolving Deepfake Technologies: Advancements, Detection Techniques, and Societal Impact. Don Bosco Institute of Technology Delhi Journal of Research. https://www.semanticscholar.org/paper/d2273fc34453ce6adc183dfdb0fcac4afa83aaa0
  • 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
  • Deloitte (2025). Generative AI is expected to magnify the risk of deepfakes and other fraud in banking. Deloitte Insights.
  • EBA/ECB joint report on payment fraud data. (2024, August 2). Global Regulation Tomorrow. https://www.regulationtomorrow.com/the-netherlands/payments-the-netherlands/eba-ecb-joint-report-on-payment-fraud-data/
  • European Banking Authority. (2024). EBA Opinion on new types of payment fraud and possible mitigants. EBA.
  • European Banking Authority & European Central Bank. (2023). Report on payment fraud. Retrieved from https://www.eba.europa.eu/publications
  • European Central Bank & European Banking Authority. (2024). ECB and EBA publish joint report on payment fraud. European Union.
  • Fariha, N. et al. (2025). Advanced fraud detection using machine learning models: enhancing financial transaction security. doi:10.48550/ARXIV.2506.10842
  • Hermosilla, P., Berríos, S., & Allende-Cid, H. (2025). Explainable AI for forensic analysis: A comparative study of SHAP and LIME in intrusion detection models. Applied Sciences, 15(13), 7329. https://doi.org/10.3390/app15137329
  • House of Commons Library. (2024). Banking fraud and scams: Research briefing. UK Parliament. Retrieved from https://commonslibrary.parliament.uk/research-briefings/
  • (2025). Top 5 cases of AI deepfake fraud from 2024 exposed. Incode.
  • Jiang, J., Zhang, C., Ke, L., Hayes, N., Zhu, Y., Qiu, H., Zhang, B., Zhou, T., & Wei, G.-W. (2025). A review of machine learning methods for imbalanced data challenges in Chemistry. Chemical Science, 16(18), 7637–7658. https://doi.org/10.1039/d5sc00270b
  • KPMG International. (2025). What we have learned from UK Finance’s latest annual fraud report. KPMG.
  • Mohamed, N. (2025). Artificial Intelligence and machine learning in cybersecurity: A deep dive into state-of-the-art techniques and future paradigms. Knowledge and Information Systems, 67(8), 6969–7055. https://doi.org/10.1007/s10115-025-02429-y
  • Najar, A. V., Alizamani, leili, Zarqi, M., & Hooshmand, E. (2025). A global scoping review on the patterns of medical fraud and abuse: Integrating data-driven detection, prevention, and legal responses. Archives of Public Health, 83(1). https://doi.org/10.1186/s13690-025-01512-8
  • Ngai, E., Hu, Y., Wong, Y., Chen, Y., & Sun, X. (2011). The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision Support Systems. https://www.sciencedirect.com/science/article/pii/S0167923610001302
  • Ngan, J. (2025). “The view from below”: Resistance and change in authorised push payment fraud. Journal of Economic Criminology, 9, 100166. https://doi.org/10.1016/j.jeconc.2025.100166
  • Onuh Matthew Ijiga, Idoko Peter Idoko, Godslove Isenyo Ebiega, Frederick Itunu Olajide, Timilehin Isaiah Olatunde, & Chukwunonso Ukaegbu. (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
  • Payment Cards & Mobile. (2025). Report: A deep dive into payment fraud in the EU.
  • Payment Systems Regulator. (2023). APP scams performance report. Retrieved from https://www.psr.org.uk/publications/app-scams-performance-reports/
  • Rao, S.X. et al. (2025). Fraud Detection in E-Commerce: A Systematic Review of Transaction Risk Prevention. IntechOpen eBooks. IntechOpen. doi:10.5772/intechopen.1009640
  • Sai, C., Amaresh, C., & Jancy, S. (2025). Online Payment Fraud Detection Using Exploratory Data Analysis. https://ieeexplore.ieee.org/abstract/document/10968090/
  • Skadden, Arps, Slate, Meagher & Flom LLP. (2024). New rules to tackle authorised push payment fraud.
  • Stoudt, S., Jernite, Y., Marshall, B., & Marwick, B. (2024). Ten simple rules for building and maintaining a responsible data science workflow. https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012232
  • Talukder, Md. A., Khalid, M., & Uddin, M. A. (2024). An integrated multistage ensemble machine learning model for fraudulent transaction detection. Journal of Big Data, 11(1). https://doi.org/10.1186/s40537-024-00996-5
  • TLT LLP. (2025). AI and financial crime – five big questions with Ben Cooper. TLT.
  • UK Finance. (2023). Fraud the facts 2023: The definitive overview of payment industry fraud. Retrieved from https://www.ukfinance.org.uk/policy-and-guidance/reports-publications/fraud-facts-2023
  • UK Finance. (2025). Annual fraud report 2025. Retrieved October 9, 2025, from https://www.ukfinance.org.uk/policy-and-guidance/reports-and-publications/annual-fraud-report-2025
  • UK Finance. (2025). Fraud continues to pose a significant threat with over £1 billion stolen in 2024. UK Finance. https://www.ukfinance.org.uk/news-and-insight/press-release/fraud-report-2025-press-releas
  • Mohamed, N. (2025) ‘Artificial Intelligence and machine learning in cybersecurity: A deep dive into state-of-the-art techniques and future paradigms’, Knowledge and Information Systems, 67(8), pp. 6969–7055. doi:10.1007/s10115-025-02429-y.
  • Rao, S.X. et al. (2025) “Fraud Detection in E-Commerce: A Systematic Review of Transaction Risk Prevention,” IntechOpen eBooks. IntechOpen. doi:10.5772/intechopen 1009640.
  • UK Finance (2025) Fraud continues to pose a significant threat with over £1 billion stolen in 2024. UK Finance. Available at: https://www.ukfinance.org.uk/news-and-insight/press-release/fraud-report-2025-press-releas