Detection of Fraudulent Transactions in the Cryptocurrency Market Using an Explainable Graph Isomorphism Network

Authors

  • Fatemeh Jalalzaei Department of Management, Science, and Technology, Amirkabir University of Technology, Tehran, Iran.
  • Akbar Esfahanipour * Department of Industrial Engineering & Management Systems, Amirkabir University of Technology, Tehran, Iran. https://orcid.org/0000-0003-3222-5186
  • Ali Reza Keivanimehr Department of Management, Science, and Technology, Amirkabir University of Technology, Tehran, Iran.

https://doi.org/10.48314/jidcm.v2i1.89

Abstract

Cryptocurrency markets are highly vulnerable to fraud due to the lack of comprehensive regulatory frameworks and the pseudonymous nature of transactions. This paper proposes a graph-based learning approach for detecting suspicious transactions in decentralized networks, with a focus on Bitcoin. We evaluate three Graph Neural Network (GNN) models: Graph Convolutional Networks (GCT), Graph Attention Networks (GAN), and Graph Isomorphism Networks (GIN). Experiments on the Elliptic dataset, which contains highly imbalanced data between legitimate and illicit transactions, show that GIN outperforms other models in detecting fraudulent patterns. To enhance interpretability and provide insights into the decision-making process of the models, we integrate explainable Artificial Intelligence (AI) techniques, specifically using GNNExplainer, which identifies the most influential nodes and features contributing to each fraud prediction. This approach not only enables analysts and regulators to understand why a transaction is classified as suspicious, improving trust and accountability in automated cryptocurrency fraud detection systems, but also achieves a high detection F1-score of 96.22% for illicit transactions using GIN.

Keywords:

Fraud detection, Graph isomorphism network, Graph neural network, Explainable artificial intelligence, Deep learning, Bitcoin

References

  1. [1] Li, X., Jiang, P., Chen, T., Luo, X., & Wen, Q. (2020). A survey on the security of blockchain systems. Future generation computer systems, 107, 841–853. https://doi.org/10.1016/j.future.2017.08.020
  2. [2] Xu, K., Hu, W., Leskovec, J., & Jegelka, S. (2018). How powerful are graph neural networks? https://doi.org/10.48550/arXiv.1810.00826
  3. [3] Nasir, W. (2026). Cryptocurrency fraud and financial crime: Analyzing convicted fraudsters in digital asset scams. Authorea, 3(12). https://doi.org/10.22541/au.174180456.65670202/v1
  4. [4] Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Žitnik, & Jure Leskovec. (2019). GNNExplainer: Generating explanations for graph neural networks. Advances in neural information processing systems (PP. 9240–9251). Curran Associates, Inc. https://pmc.ncbi.nlm.nih.gov/articles/PMC7138248/
  5. [5] Liu, S., Cui, B., & Hou, W. (2024). A survey on blockchain abnormal transaction detection. Blockchain and trustworthy systems (pp. 211–225). Singapore: Springer Nature Singapore. https://doi.org/10.1007/978-981-99-8101-4_15
  6. [6] Bandarupalli, G. (2025). The evolution of blockchain security and examining machine learning’s impact on ethereum fraud detection. 2025 17th international conference on electronics, computers and artificial intelligence (ECAI) (pp. 1–6). IEEE. https://doi.org/10.1109/ECAI65401.2025.11095594
  7. [7] Ashfaq, T., Khalid, R., Yahaya, A. S., Aslam, S., Azar, A. T., Alsafari, S., & Hameed, I. A. (2022). A machine learning and blockchain based efficient fraud detection mechanism. Sensors, 22(19), 7162. https://doi.org/10.3390/s22197162
  8. [8] Asiri, A., & Somasundaram, K. (2025). Graph convolution network for fraud detection in bitcoin transactions. Scientific reports, 15(1), 11076. https://doi.org/10.1038/s41598-025-95672-w
  9. [9] Marasi, S., & Ferretti, S. (2024). Anti-money laundering in cryptocurrencies through graph neural networks: A comparative study. 2024 IEEE 21st consumer communications & networking conference (CCNC) (pp. 272–277). IEEE. https://doi.org/10.1109/CCNC51664.2024.10454631
  10. [10] Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision (pp. 2980-2988). IEEE. https://doi.org/10.1109/ICCV.2017.324
  11. [11] Chen, Y., Tang, X., Qi, X., Li, C. G., & Xiao, R. (2022). Learning graph normalization for graph neural networks. Neurocomputing, 493, 613–625. https://doi.org/10.1016/j.neucom.2022.01.003
  12. [12] Jiang, B., Zhang, Z., Lin, D., Tang, J., & Luo, B. (2019). Semi-supervised learning with graph learning-convolutional networks. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 11313-11320). IEEE. https://doi.org/10.1109/CVPR.2019.01157
  13. [13] Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2017). Graph attention networks. https://info.arxiv.org/help/api/index
  14. [14] Li, K., Yang, T., Zhou, M., Meng, J., Wang, S., Wu, Y., …, & Tong, Y. (2024). SEFraud: Graph-based self-explainable fraud detection via interpretative mask learning. Proceedings of the 30th ACM sigkdd conference on knowledge discovery and data mining (pp. 5329–5338). New York, NY, USA: Association for Computing Machinery. https://doi.org/10.1145/3637528.3671534

Published

2026-03-04

Issue

Vol. 2 No. 1 (2026): Journal of Intelligent Decision and Computational Modelling

Section

Articles

License

Copyright (c) 2026 Journal of Intelligent Decision and Computational Modelling

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Jalalzaei, F. ., Esfahanipour, A. ., & Keivanimehr, A. R. . (2026). Detection of Fraudulent Transactions in the Cryptocurrency Market Using an Explainable Graph Isomorphism Network. Journal of Intelligent Decision and Computational Modelling, 2(1), 50-57. https://doi.org/10.48314/jidcm.v2i1.89

Similar Articles

1-10 of 15

You may also start an advanced similarity search for this article.