Hybrid Framework of Graph Neural Networks, Federated Learning and Explainable Artificial Intelligence for Real-Time Fraud Detection and Anti-Money Laundering

The increased sophistication of fraudulent schemes and money laundering techniques is placing significant pressure on conventional fraud detection systems and models. This study presents a hybrid framework that integrates Graph Neural Networks, Federated Learning and Explainable Artificial Intelligence for real-time fraud detection and anti-money laundering in digital financial systems. The framework uses graph neural networks to learn heterogeneous financial transaction graphs which helps to uncover organized fraud committed by fraudsters. Federated learning was leveraged in this study to collaboratively train global graph neural network fraud detection model while protecting the privacy of the contributing banks using differential privacy. In addition, the framework was supplemented with explainable artificial intelligence, namely SHAP and GNNExplainer to enhance the model’s interpretability. The proposed framework was benchmarked against conventional machine learning algorithms, deep learning and graph neural networks on the SynthAML dataset which contains more than 16 million transactions in a large-scale graph. The evaluation results revealed that the framework achieved an accuracy of 97.6%, precision of 95.7%, recall of 92.6%, F1-score of 94.1% and ROC-AUC of 0.984. The framework had better performance compared to conventional fraud detection models, deep learning and graph neural networks. In federated learning experiments, the proposed graph neural networks converged within fifty communication rounds while achieving reasonable performance with minimal communication overhead. Specifically, the performance decreased by only 0.8% when applying differential privacy for the model. Additionally, the explainability component of the framework achieved a faithfulness score of 0.913. In conclusion, the hybrid framework outperformed conventional fraud detection models, deep learning and graph neural networks. The framework can be leveraged for fraud detection and anti-money laundering detection in digital financial systems.

Fraud Detection; Anti-Money Laundering; Graph Neural Networks; Federated Learning

1. Ahamed, F., & Shukla, V. K. (2023, March). The rise of the Omani digital payment sector: Trends, adoption, and future. In 2023 International Conference on Computational Intelligence and Knowledge Economy (ICCIKE) (pp. 181–185). IEEE. [Google Scholar] [Crossref]

2. Al Ghunaimi, H., Almaqtari, F. A., Wesonga, R., & Elmashtawy, A. (2025). The rise of FinTech and the journey toward a cashless society: Investigating the use of mobile payments by SMEs in Oman in the context of Vision 2040. Administrative Sciences, 15(5), 178. https://doi.org/10.3390/admsci15050178 [Google Scholar] [Crossref]

3. Foster, G., & Miller, J. (2022). The challenges of digital payment integration for small businesses. Journal of Finance and Business Economics, 41(2), 201–215. [Google Scholar] [Crossref]

4. Hilal, A. A., Hilal, T. A., & Hilal, H. A. (2023). Investigating the failure of the blockchain technology and suggested recommendations. Procedia Computer Science, 224, 450–455. [Google Scholar] [Crossref]

5. Jensen, R. I. T., Ferwerda, J., Jørgensen, K. S., et al. (2023). A synthetic data set to benchmark anti-money laundering methods. Scientific Data, 10(661). https://doi.org/10.1038/s41597-023-02569-2 [Google Scholar] [Crossref]

6. Khan, A. (2021). Mobile payments and digital financial inclusion: A systematic review. Journal of Financial Technology and Innovation, 7(1), 45–60. [Google Scholar] [Crossref]

7. Liu, Y., Li, L., Cao, L., & Zhang, Y. (2022). Machine learning for financial fraud detection: A comprehensive survey. IEEE Transactions on Neural Networks and Learning Systems, 33(8), 3474–3491. https://doi.org/10.1109/TNNLS.2021.3063099 [Google Scholar] [Crossref]

8. Nelson, J., Owen, J., & Kagami, A. (2025). Improving fraud detection with advanced techniques. [Google Scholar] [Crossref]

9. Obaze, C. A., Omorogie, M., Odeh, C., Azaka, M., Nwakeze, O. M., & Ezekiel, O. C. L. (2025, October 25). Fraud detection in financial transactions using ensemble machine learning models. RSIS, 12(13), 27–36. Special Issue on Emerging Paradigms in Computer Science and Technology. [Google Scholar] [Crossref]

10. Pillai, S. E. V. S., Nadella, G. S., Meduri, K., Priyadharsini, N. A., Bhuvanesh, A., & Kumar, D. (2025). A Walrus optimization-enhanced long short-term memory model for credit fraud detection in banking. International Journal of Information Technology, 1–17. [Google Scholar] [Crossref]

11. Tiwari, P., Mehta, S., Sakhuja, N., Kumar, J., & Singh, A. K. (2021). Credit card fraud detection using machine learning: A study. arXiv preprint arXiv:2108.10005. [Google Scholar] [Crossref]

12. Vallarino, D. (2025, March 7). AI-powered fraud detection in financial services: GNN, compliance challenges, and risk mitigation. SSRN. https://ssrn.com/abstract=5170054 or http://dx.doi.org/10.2139/ssrn.5170054 [Google Scholar] [Crossref]

13. Wang, J., & Liu, Q. (2023). Advancements in AI and machine learning for financial fraud detection. International Journal of Data Science, 10(4), 232–245. [Google Scholar] [Crossref]

14. Xu, J., Yang, T., Zhuang, S., Li, H., & Lu, W. (2024). AI-based financial transaction monitoring and fraud prevention with behaviour prediction. Applied Computational Engineering, 67, 76–82. https://doi.org/10.54254/2755-2721/67/2024ma0068 [Google Scholar] [Crossref]

15. Yang, H., Shukur, Z., & Sahran, S. (2026). A review of artificial intelligence for financial fraud detection. Applied Sciences, 16(4), 1931. https://doi.org/10.3390/app16041931 [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet