Ethereum phishing detection based on graph neural networks

• Published in: IET blockchain Vol. 4; no. 3; pp. 226 - 234
• Main Authors: Xiong, Ao, Tong, Yuanzheng, Jiang, Chengling, Guo, Shaoyong, Shao, Sujie, Huang, Jing, Wang, Wei, Qi, Baozhen
• Format: Journal Article
• Language: English
• Published: Shanghai John Wiley & Sons, Inc 01.09.2024; Wiley
• Subjects: Algorithms; anomaly detection; Blockchain; Classification; cryptocurrency; Cybercrime; Datasets; Digital currencies; Ethereum; Feature extraction; Fraud; GNN; Graph neural networks; Graphs; Machine learning; Malware; Methods; Neural networks; Pattern recognition; Phishing; phishing detection; Random walk
• ISSN: 2634-1573; 2634-1573
• DOI: 10.1049/blc2.12031

With the development of blockchain, cryptocurrencies are also showing a boom. However, due to the decentralized and anonymous nature of blockchain, cryptocurrencies have inevitably become a hotbed for fraudulent crimes. For example, phishing scams are frequent, which not only jeopardize the financial security of blockchain, but also hinder the promotion of blockchain technology. To solve this problem, this paper proposes a graph neural network‐based phishing detection method for Ethereum, and validates it using Ethereum datasets. Specifically, this paper proposes a feature learning algorithm named TransWalk, which consists of a random walk strategy for transaction networks and a multi‐scale feature extraction method for Ethereum. Then, an Ethereum phishing fraud detection framework is built based on TransWalk, and conduct extensive experiments on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection. A feature learning algorithm named TransWalk is proposed, which consists of a random walk strategy for transaction net‐works and a multi‐scale feature extraction method for Ethereum. Then, an Ethereum phishing fraud detection framework based on TransWalk is built, and extensive experiments are conducted on the Ethereum dataset to verify the effectiveness of this scheme in identifying Ethereum phishing detection.