Multi‐Distance Spatial‐Temporal Graph Neural Network for Anomaly Detection in Blockchain Transactions
Top Cited Papers
Open Access
- 30 January 2025
- journal article
- research article
- Published by Wiley in Advanced Intelligent Systems
- Vol. 7 (8)
Abstract
This article presents MDST‐GNN, a multi‐distance spatial‐temporal graph neural network for blockchain anomaly detection. To address challenges in detecting fraudulent cryptocurrency transactions, MDST‐GNN integrates a multi‐distance graph convolutional architecture with adaptive temporal modeling, enabling capture of both local and global spatial dependencies while inferring patterns from anonymized temporal data. The model incorporates self‐supervised learning to enhance generalization ability. Experiments on the Elliptic dataset demonstrate MDST‐GNN's superior performance over state‐of‐the‐art methods, achieving improvements of 1.5% in AUC‐ROC and 2.9% in AUC‐PR. The model's robustness to temporal granularity and effectiveness in identifying suspicious transactions underscore its practical value for blockchain forensics.Keywords
This publication has 29 references indexed in Scilit:
- DA-GNN: A smart contract vulnerability detection method based on Dual Attention Graph Neural NetworkComputer Networks, 2024
- Determinants of the price of bitcoin: An analysis with machine learning and interpretability techniquesInternational Review of Economics & Finance, 2024
- Toward interpretable credit scoring: integrating explainable artificial intelligence with deep learning for credit card default predictionNeural Computing and Applications, 2023
- Enhancing financial fraud detection with hierarchical graph attention networks: A study on integrating local and extensive structural informationFinance Research Letters, 2023
- Graph Neural Network-Based Anomaly Detection in Blockchain Network2023
- State of the Art Literature on Anti-money Laundering Using Machine Learning and Deep Learning Techniques2023
- Anomaly detection in Internet of medical Things with Blockchain from the perspective of deep neural networkInformation Sciences, 2022
- Privacy-preserving blockchain-based federated learning for traffic flow predictionFuture Generation Computer Systems, 2021
- Smart Contract Vulnerability Detection Based on Dual Attention Graph Convolutional Network2021
- Deep learning for financial applications : A surveyApplied Soft Computing, 2020