TY - JOUR
T1 - CMD-EPD
T2 - A Graph Contrastive Learning Framework with Multi-Dimensional Fusion for Ethereum Phishing Detection
AU - Yan, Chuyi
AU - Qi, Yinhao
AU - Han, Xueying
AU - Liu, Junrong
AU - Du, Dan
AU - Lu, Zhigang
AU - Shen, Meng
AU - Liu, Yuling
N1 - Publisher Copyright:
© 2026 Copyright held by the owner/author(s).
PY - 2026/6/11
Y1 - 2026/6/11
N2 - The burgeoning prevalence of Ethereum phishing behavior has iCSUR-2025-0155mposed substantial constraints on the advancement of blockchain finance, resulting in losses of more than $7.7 billion to date, so it is urgent to detect it in time. Currently, available detection methods usually focus on the spatial features within transaction graphs. These methods often employ shallow mining techniques on small samples. As a result, they may overlook certain aspects of interaction patterns, such as temporal behavior. Additionally, their data mining capability is limited due to the small sample sizes. In this study, we propose a graph contrastive learning framework to enrich features of accounts behavior patterns with restricted samples to overcome these limitations. Firstly, we construct an Ethereum interaction graph with the multi-graph involving more temporal information centered with labeled nodes and lighten it with our strategy. Secondly, to comprehensively characterize the accounts pattern, we design the encoder part with the GAT-LSTM model based on attention mechanism fusing statistical features, fine-grained temporal behavioral features and graph structural semantic features. Thirdly, to moderate the sparsity of phishing nodes, we employ data augmentation and contrastive learning to fully mine sparse node information. Moreover, we carried out an in-depth experimental evaluation. The CMD-EPD approach, boasting an F 1-score of 0.87, outperformed all comparison methods. We also executed a thorough case study to analyze phishing accounts phenomenological indicators which back up the superiority of our framework.
AB - The burgeoning prevalence of Ethereum phishing behavior has iCSUR-2025-0155mposed substantial constraints on the advancement of blockchain finance, resulting in losses of more than $7.7 billion to date, so it is urgent to detect it in time. Currently, available detection methods usually focus on the spatial features within transaction graphs. These methods often employ shallow mining techniques on small samples. As a result, they may overlook certain aspects of interaction patterns, such as temporal behavior. Additionally, their data mining capability is limited due to the small sample sizes. In this study, we propose a graph contrastive learning framework to enrich features of accounts behavior patterns with restricted samples to overcome these limitations. Firstly, we construct an Ethereum interaction graph with the multi-graph involving more temporal information centered with labeled nodes and lighten it with our strategy. Secondly, to comprehensively characterize the accounts pattern, we design the encoder part with the GAT-LSTM model based on attention mechanism fusing statistical features, fine-grained temporal behavioral features and graph structural semantic features. Thirdly, to moderate the sparsity of phishing nodes, we employ data augmentation and contrastive learning to fully mine sparse node information. Moreover, we carried out an in-depth experimental evaluation. The CMD-EPD approach, boasting an F 1-score of 0.87, outperformed all comparison methods. We also executed a thorough case study to analyze phishing accounts phenomenological indicators which back up the superiority of our framework.
KW - Blockchain
KW - behavior analysis
KW - contrastive learning
KW - ethereum
KW - phishing detection
UR - https://www.scopus.com/pages/publications/105050426428
U2 - 10.1145/3812797
DO - 10.1145/3812797
M3 - Article
AN - SCOPUS:105050426428
SN - 2471-2566
VL - 29
JO - ACM Transactions on Privacy and Security
JF - ACM Transactions on Privacy and Security
IS - 3
M1 - 29
ER -