Hybrid GCN-GRU Model for Anomaly Detection in Cryptocurrency Transactions

2025/09/09 by Gyuyeon Na, Na, Gyuyeon, Minjung Park +13
Business, Management and Accounting · Computer Science · #Artificial Intelligence (cs.AI) #Blockchain Technology Applications and Security #FOS: Computer and information sciences #Financial Distress and Bankruptcy Prediction #Imbalanced Data Classification Techniques #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2509.07392

openalex publication_date 2025/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• SoK: A Survey of Mixing Techniques and Mixers for Cryptocurrencies
• Topological Analysis of Mixer Activities in the Bitcoin Network
• Detecting Anomalies in Blockchain Transactions using Machine Learning Classifiers and Explainability Analysis
• A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data
• Transaction Fraud Detection Using GRU-centered Sandwich-structured Model
• Anomaly Detection in Bitcoin Network Using Unsupervised Learning Methods
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Related

• Probabilistic Sampling-Enhanced Temporal-Spatial GCN: A Scalable Framework for Transaction Anomaly Detection in Ethereum Networks
• Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensics
• Graph Network Models To Detect Illicit Transactions In Block Chain
• Anomaly Detection for Fraud in Cryptocurrency Time Series
• HyPV-LEAD: Proactive Early-Warning of Cryptocurrency Anomalies through Data-Driven Structural-Temporal Modeling