Blockchain transaction networks are complex, with evolving temporal patterns and inter-node relationships. To detect illicit activities, we propose a hybrid GCN-GRU model that captures both structural and sequential features. Using real Bitcoin transaction data (2020-2024), our model achieved 0.9470 Accuracy and 0.9807 AUC-ROC, outperforming all baselines.
@article{arxiv.2509.07392,
title = {Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions},
author = {Gyuyeon Na and Minjung Park and Hyeonjeong Cha and Soyoun Kim and Sunyoung Moon and Sua Lee and Jaeyoung Choi and Hyemin Lee and Sangmi Chai},
journal= {arXiv preprint arXiv:2509.07392},
year = {2025}
}