Abstract
Ethereum fraud detection is crucial for maintaining the security and trustworthiness of blockchain ecosystems. This paper proposes STGraph-FS, a novel framework that combines structural temporal graph neural networks with feature selection techniques for effective Ethereum fraud detection. Our approach captures both the structural properties of transaction networks and their temporal evolution patterns, while simultaneously identifying the most relevant features for fraud detection. Experimental results demonstrate the effectiveness of our method in detecting fraudulent activities in Ethereum networks.
Abstract
Ethereum fraud detection is crucial for maintaining the security and trustworthiness of blockchain ecosystems. This paper proposes STGraph-FS, a novel framework that combines structural temporal graph neural networks with feature selection techniques for effective Ethereum fraud detection. Our approach captures both the structural properties of transaction networks and their temporal evolution patterns, while simultaneously identifying the most relevant features for fraud detection. Experimental results demonstrate the effectiveness of our method in detecting fraudulent activities in Ethereum networks.
Key Contributions
- Structural Temporal Graph Framework: Novel integration of structural and temporal information in Ethereum transaction networks
- Feature Selection: Adaptive feature selection mechanism for identifying relevant fraud indicators
- Comprehensive Evaluation: Extensive experiments on real-world Ethereum transaction data
- Superior Performance: Improved detection accuracy compared to existing methods
Keywords
Ethereum, Fraud Detection, Graph Neural Networks, Feature Selection, Blockchain Security, Temporal Graphs