Federated Graph Learning for Cross-Institution Money-Laundering Detection on Heterogeneous Transaction Networks

Article Sidebar

PDF
Published: 2026-02-21
Keywords:
federated learning, graph neural networks, transaction networks, privacy preservation, money-laundering detection

Main Article Content

Emma Virtanen
Department of Computer Science, University of Helsinki, Helsinki, 00014, Finland
Sanna Korhonen
Department of Computer Science, University of Helsinki, Helsinki, 00014, Finland
Oskari Heikkilä
Department of Computer Science, University of Helsinki, Helsinki, 00014, Finland
Lauri Nieminen
Department of Computer Science, University of Helsinki, Helsinki, 00014, Finland

Abstract

This study proposes a federated graph-learning framework for detecting money-laundering activities across financial institutions without sharing raw customer data. Four banks participated in local training using transaction-graph structures containing 15.7 million nodes and 112.5 million edges. A global aggregation mechanism was used to synchronize encrypted model parameters. Compared with local graph models, the federated framework improved the average AUC from 0.84 to 0.90 and increased precision at 10% recall by 29.7%. Robustness tests showed stable performance even when one institution exhibited severe label imbalance. Differential-privacy noise prevented reconstruction of sensitive records under gradient-inversion tests. The results confirm that cross-institution modeling can significantly enhance detection accuracy while maintaining data confidentiality.

Article Details

Issue

Vol. 2 No. 1 (2026)

Section

Articles

How to Cite

Federated Graph Learning for Cross-Institution Money-Laundering Detection on Heterogeneous Transaction Networks. (2026). Journal of Sustainability, Policy, and Practice, 2(1), 162-167. https://schoalrx.com/index.php/jspp/article/view/86

References

1. J. Castelao-López, T. Corzo Santamaría, and D. Lagoa-Varela, "Analysis of the main techniques and tools to combat money laundering: A review of the literature," Journal of Money Laundering Control, 2025. doi: 10.1108/jmlc-10-2024-0159

2. S. Barcio, "Network analysis enhancements to improve anti-money laundering transaction monitoring systems in banks (Doctoral dissertation, Politecnico di Torino)," 2025.

3. A. M. Kanca, ", & Türker, İ," (2025). A systematic review of graph-based representation techniques for cyber-attack detection across application domains. Concurrency and Computation: Practice and Experience, vol. 37, no. 27-28, p. e70389, 2025.

4. Z. Amiri, A. Heidari, N. J. Navimipour, M. Unal, and A. Mousavi, "Adventures in data analysis: A systematic review of deep learning techniques for pattern recognition in cyber-physical-social systems," Multimedia Tools and Applications, vol. 83, no. 8, pp. 22909-22973, 2024. doi: 10.1007/s11042-023-16382-x

5. X. Gu, M. Liu, and J. Yang, "Application and effectiveness evaluation of federated learning methods in anti-money laundering collaborative modeling across inter-institutional transaction networks," 2025. doi: 10.20944/preprints202510.1828.v1

6. M. M. Fouda, Z. M. Fadlullah, M. I. Ibrahem, and N. Kato, "Privacy-preserving data-driven learning models for emerging communication networks: A comprehensive survey," IEEE Communications Surveys & Tutorials, 2024. doi: 10.1109/comst.2024.3486690

7. E. Tanuwijaya, and T. Mauritsius, "Anomaly detection in sales transactions for FMCG (fast moving consumer goods) distribution," Journal of Applied Data Sciences, vol. 5, no. 3, pp. 1223-1236, 2024.

8. Y. Yang, M. Guo, E. A. Corona, B. Daniel, C. Leuze, and F. Baik, "VR MRI training for adolescents: A comparative study of gamified VR, passive VR, 360 video, and traditional educational video," arXiv preprint, 2025.

9. T. K. Chowdhury, and S. P. Kudapa, "Federated learning models for privacy-preserving data sharing and secure analytics in healthcare industry," International Journal of Business and Economics Insights, vol. 4, no. 4, pp. 91-133, 2024.

10. W. Zhu, Y. Yao, and J. Yang, "Real-time risk control effects of digital compliance dashboards: An empirical study across multiple enterprises using process mining, anomaly detection, and interrupted time series," 2025.

11. S. A. Tanim, M. F. Mridha, M. Safran, S. Alfarhood, and D. Che, "Secure federated learning for Parkinson's disease: Non-IID data partitioning and homomorphic encryption strategies," IEEE Access, 2024. doi: 10.1109/access.2024.3454690

12. W. Bai, "Phishing website detection based on machine learning algorithm," In Proceedings of the 2020 International Conference on Computing and Data Science, 2020, pp. 293-298. doi: 10.1109/cds49703.2020.00064

13. A. Hatamizadeh, H. Yin, P. Molchanov, A. Myronenko, W. Li, P. Dogra, and H. R. ... Roth, "Do gradient inversion attacks make federated learning unsafe? IEEE Transactions on Medical Imaging, 42(7), 2044-2056," 2023.

14. J. B. Sheu, and X. Q. Gao, "Alliance or no alliance-Bargaining power in competing reverse supply chains," European Journal of Operational Research, vol. 233, no. 2, pp. 313-325, 2014.

15. W. Zhu, Y. Yao, and J. Yang, "Optimizing financial risk control for multinational projects: A joint framework based on CVaR-robust optimization and panel quantile regression," 2025. doi: 10.20944/preprints202510.1345.v1

16. M. Rahmati, "Real-time financial fraud detection using adaptive graph neural networks and federated learning," International Journal of Management and Data Analytics, vol. 5, no. 1, pp. 98-110, 2025. doi: 10.21203/rs.3.rs-6026136/v1

17. J. Wang, and Y. Xiao, "Research on credit risk forecasting and stress testing for consumer finance portfolios based on macroeconomic scenarios," 2025. doi: 10.1145/3785706.3785751

18. P. Rot, K. Grm, P. Peer, and V. Štruc, "PrivacyProber: Assessment and detection of soft-biometric privacy-enhancing techniques," IEEE Transactions on Dependable and Secure Computing, vol. 21, no. 4, pp. 2869-2887, 2023. doi: 10.1109/tdsc.2023.3319500

19. T. Li, Y. Jiang, E. Hong, and S. Liu, "Organizational development in high-growth biopharmaceutical companies: A data-driven approach to talent pipeline and competency modeling," 2025. doi: 10.20944/preprints202511.0631.v1

20. Z. Hu, Y. Hu, and H. Li, "Multi-task temporal fusion transformer for joint sales and inventory forecasting in Amazon e-commerce supply chain," arXiv preprint, 2025.