CMD-EPD: A Graph Contrastive Learning Framework with Multi-Dimensional Fusion for Ethereum Phishing Detection
Open Access
- 11 June 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 29 (3) , 1-28
Abstract
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.Keywords
Funding Information
- National Key Research and Development Program of China (No.2021YFF0307203, No.2019QY1300)
- Youth Innovation Promotion Association of the Chinese Academy of Sciences (2021156)
- Strategic Priority Research Program of Chinese Academy of Sciences (XDC02040100)
- National Natural Science Foundation of China (61802404)
- Program of Key Laboratory of Network Assessment Technology
- Chinese Academy of Sciences
- Program of Beijing Key Laboratory of Network Security and Protection Technology
This publication has 13 references indexed in Scilit:
- Temporal high-order proximity aware behavior analysis on EthereumWorld Wide Web, 2021
- Community Detection in Blockchain Social NetworksJournal of Communications and Information Networks, 2021
- Internet Financial Fraud Detection Based on a Distributed Big Data Approach With Node2vecIEEE Access, 2021
- Phishing Scams Detection in Ethereum Transaction NetworkACM Transactions on Internet Technology, 2020
- T-EDGE: Temporal WEighted MultiDiGraph Embedding for Ethereum Transaction Network AnalysisFrontiers in Physics, 2020
- Blockchain and Cryptocurrencies: Model, Techniques, and ApplicationsIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2018
- A selective overview of feature screening for ultrahigh-dimensional dataScience China Mathematics, 2015
- DeepWalk2014
- Principal component analysisWIREs Computational Statistics, 2010
- Random ForestsMachine Learning, 2001