Privacy-Preserving Artificial Intelligence for Financial and Organizational Risk Analytics Using Federated Learning and Differential Privacy
American Journal of Interdisciplinary Studies · 01.10.2026 · 16 (10) · 01-50
DOI: 10.63125/4zcpqs88 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Interdisciplinary Studies, online erschienen am 01.10.2026. Verfasst von Masrul Hasan und 1 weiteren Autor:innen.
Abstract (Originalsprache)
This study investigates the integration of federated learning (FL) and formal differential privacy (DP) to resolve the fundamental trade-off between institutional data sovereignty and collaborative risk intelligence across banking, financial technology (FinTech), and enterprise cybersecurity domains. Utilizing a harmonized cross-silo dataset of 2,410,000 verified observations partitioned across 25 institutional nodes, the research systematically evaluated centralized non-private learning (CNPL), isolated local institutional learning (LIL), conventional federated learning (FL), and differentially private federated learning (DP-FL) across transactional fraud detection, credit-default forecasting, and enterprise intrusion identification. Empirical findings revealed that conventional FL achieved near-parity with centralized baselines, preserving over 97% of optimal predictive utility with a financial fraud F1-score of 0.847 and cybersecurity F1-score of 0.871, compared to isolated local learning baselines of 0.674 and 0.651, respectively. Enforcing formal differential privacy ($\epsilon = 4.0, \delta = 10^{-5}$) incurred non-linear utility penalties concentrated primarily on rare-event detection, yielding F1-scores of 0.759 for fraud and 0.775 for cyber intrusions, with false-negative rates rising to 25.90%. Moderation and regression analyses demonstrated that institutional volume ($\beta = 0.294, p < 0.001$) significantly buffered privacy-induced degradation, while severe class imbalance ($IR < 0.02$) compounded performance losses. Mediation modeling confirmed that stochastic gradient variance accounted for 40.8% of privacy-induced utility erosion. Adversarial evaluations established that conventional FL remained vulnerable to membership inference (71.40% accuracy; AUC = 0.785) and gradient reconstruction (cosine similarity = 0.842), whereas DP-FL effectively neutralized leakage to random chance (51.60% accuracy; AUC = 0.521; similarity = 0.084). Multi-objective Pareto optimization identified moderate privacy expenditures ($\epsilon = 4.0$) as the optimal configuration, achieving the highest Composite Utility-Privacy Index (CUPI = 0.844) while capping training extension at 44.5 wall-clock hours and 52.86 GB cumulative network egress. These findings validate privacy-preserving collaborative artificial intelligence as an empirically reliable, computationally viable architecture for institutional risk mitigation.
Zitieren
APA
Hasan, M., & Waliullah, M. (2026). Privacy-Preserving Artificial Intelligence for Financial and Organizational Risk Analytics Using Federated Learning and Differential Privacy. American Journal of Interdisciplinary Studies, 16(10), 01-50. https://doi.org/10.63125/4zcpqs88
Vancouver
Hasan M, Waliullah M. Privacy-Preserving Artificial Intelligence for Financial and Organizational Risk Analytics Using Federated Learning and Differential Privacy. American Journal of Interdisciplinary Studies. 2026;16(10):01-50. doi:10.63125/4zcpqs88
BibTeX
@article{Hasan2026,
author = {Hasan, Masrul and Waliullah, Md},
title = {Privacy-Preserving Artificial Intelligence for Financial and Organizational Risk Analytics Using Federated Learning and Differential Privacy},
journal = {American Journal of Interdisciplinary Studies},
year = {2026},
volume = {16},
number = {10},
pages = {01--50},
doi = {10.63125/4zcpqs88}
}
EUVIMED