Ethereum Smart Contract Account Classification and Transaction Prediction Using the Graph Attention Network

IF 0.7 4区计算机科学 Q4 COMPUTER SCIENCE, SOFTWARE ENGINEERING

Journal of Web Engineering Pub Date : 2024-07-01 DOI:10.13052/jwe1540-9589.2353

Hankyeong Ko;Sangji Lee;Jungwon Seo

{"title":"Ethereum Smart Contract Account Classification and Transaction Prediction Using the Graph Attention Network","authors":"Hankyeong Ko;Sangji Lee;Jungwon Seo","doi":"10.13052/jwe1540-9589.2353","DOIUrl":null,"url":null,"abstract":"This study explores the application of a Graph Attention Networks version 2 (GATv2) model in analyzing the Ethereum blockchain network, addressing the challenge posed by its inherent anonymity. We constructed a heterogeneous graph representation of the network to categorize contract accounts (CAs) into different decentralized application (DApp) categories, such as DeFi, gaming, and NFT markets, using transaction history data. Additionally, we developed a link prediction model to forecast transactions between externally owned accounts (EOAs) and CAs. Our results demonstrated the effectiveness of the heterogeneous graph model in improving node embedding expressiveness and enhancing transaction prediction accuracy. The study offers practical tools for analyzing DApp flows within the Web3 ecosystem, facilitating the automatic prediction of CA service categories and identifying active DApp usage. While currently focused on the Ethereum network, future research could expand to include layer 2 networks like Arbitrum One, Optimism, and Polygon, thereby broadening the scope of analysis in the evolving blockchain landscape.","PeriodicalId":49952,"journal":{"name":"Journal of Web Engineering","volume":"23 5","pages":"657-680"},"PeriodicalIF":0.7000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10654715","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Web Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10654715/","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}

引用次数: 0

Abstract

This study explores the application of a Graph Attention Networks version 2 (GATv2) model in analyzing the Ethereum blockchain network, addressing the challenge posed by its inherent anonymity. We constructed a heterogeneous graph representation of the network to categorize contract accounts (CAs) into different decentralized application (DApp) categories, such as DeFi, gaming, and NFT markets, using transaction history data. Additionally, we developed a link prediction model to forecast transactions between externally owned accounts (EOAs) and CAs. Our results demonstrated the effectiveness of the heterogeneous graph model in improving node embedding expressiveness and enhancing transaction prediction accuracy. The study offers practical tools for analyzing DApp flows within the Web3 ecosystem, facilitating the automatic prediction of CA service categories and identifying active DApp usage. While currently focused on the Ethereum network, future research could expand to include layer 2 networks like Arbitrum One, Optimism, and Polygon, thereby broadening the scope of analysis in the evolving blockchain landscape.

查看原文本刊更多论文

使用图形注意力网络进行以太坊智能合约账户分类和交易预测

本研究探索了图形注意力网络第 2 版（GATv2）模型在分析以太坊区块链网络中的应用，以应对其固有的匿名性所带来的挑战。我们构建了网络的异构图表示法，利用交易历史数据将合约账户（CA）分为不同的去中心化应用（DApp）类别，如 DeFi、游戏和 NFT 市场。此外，我们还开发了一个链接预测模型，用于预测外部所有账户（EOA）和 CA 之间的交易。我们的研究结果表明，异构图模型在提高节点嵌入表现力和交易预测准确性方面非常有效。这项研究为分析 Web3 生态系统内的 DApp 流量提供了实用工具，有助于自动预测 CA 服务类别和识别活跃的 DApp 使用情况。虽然目前的研究重点是以太坊网络，但未来的研究可以扩展到 Arbitrum One、Optimism 和 Polygon 等第 2 层网络，从而在不断发展的区块链环境中扩大分析范围。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of Web Engineering 工程技术-计算机：理论方法

CiteScore

1.80

自引率

12.50%

发文量

审稿时长

9 months

期刊介绍： The World Wide Web and its associated technologies have become a major implementation and delivery platform for a large variety of applications, ranging from simple institutional information Web sites to sophisticated supply-chain management systems, financial applications, e-government, distance learning, and entertainment, among others. Such applications, in addition to their intrinsic functionality, also exhibit the more complex behavior of distributed applications.