Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Na, Gyuyeon, Park, Minjung, Cha, Hyeonjeong, Kim, Soyoun, Moon, Sunyoung, Lee, Sua, Choi, Jaeyoung, Lee, Hyemin, Chai, Sangmi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912578174713856
author Na, Gyuyeon
Park, Minjung
Cha, Hyeonjeong
Kim, Soyoun
Moon, Sunyoung
Lee, Sua
Choi, Jaeyoung
Lee, Hyemin
Chai, Sangmi
author_facet Na, Gyuyeon
Park, Minjung
Cha, Hyeonjeong
Kim, Soyoun
Moon, Sunyoung
Lee, Sua
Choi, Jaeyoung
Lee, Hyemin
Chai, Sangmi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07392
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions
Na, Gyuyeon
Park, Minjung
Cha, Hyeonjeong
Kim, Soyoun
Moon, Sunyoung
Lee, Sua
Choi, Jaeyoung
Lee, Hyemin
Chai, Sangmi
Machine Learning
Artificial Intelligence
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.
title Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.07392