Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum

The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Miao, Shuyi, Qiu, Wangjie, Zheng, Hongwei, Zhang, Qinnan, Tu, Xiaofan, Liu, Xunan, Liu, Yang, Dong, Jin, Zheng, Zhiming
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Miao, Shuyi
Qiu, Wangjie
Zheng, Hongwei
Zhang, Qinnan
Tu, Xiaofan
Liu, Xunan
Liu, Yang
Dong, Jin
Zheng, Zhiming
description The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money laundering, are rampant in the blockchain ecosystem and seriously threaten its integrity and security. In this paper, we propose a novel double graph-based Ethereum account de-anonymization inference method, dubbed DBG4ETH, which aims to capture the behavioral patterns of accounts comprehensively and has more robust analytical and judgment capabilities for current complex and continuously generated transaction behaviors. Specifically, we first construct a global static graph to build complex interactions between the various account nodes for all transaction data. Then, we also construct a local dynamic graph to learn about the gradual evolution of transactions over different periods. Different graphs focus on information from different perspectives, and features of global and local, static and dynamic transaction graphs are available through DBG4ETH. In addition, we propose an adaptive confidence calibration method to predict the results by feeding the calibrated weighted prediction values into the classifier. Experimental results show that DBG4ETH achieves state-of-the-art results in the account identification task, improving the F1-score by at least 3.75% and up to 40.52% compared to processing each graph type individually and outperforming similar account identity inference methods by 5.23% to 12.91%.
doi_str_mv 10.48550/arxiv.2411.18875
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2411_18875</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2411_18875</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2411_188753</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjE01DO0sDA35WQI8c7LL1eIzC8tUnBMTs4vzSuxUnDJL03KSVVwL0osyFDwzEtLLUrNS07VTUosTk2BqVJwSdVNzMvPq8zNrEosyczPUwAi15IMoNrSXB4G1rTEnOJUXijNzSDv5hri7KELtj--oCgzN7GoMh7kjniwO4wJqwAAzFs9ww</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum</title><source>arXiv.org</source><creator>Miao, Shuyi ; Qiu, Wangjie ; Zheng, Hongwei ; Zhang, Qinnan ; Tu, Xiaofan ; Liu, Xunan ; Liu, Yang ; Dong, Jin ; Zheng, Zhiming</creator><creatorcontrib>Miao, Shuyi ; Qiu, Wangjie ; Zheng, Hongwei ; Zhang, Qinnan ; Tu, Xiaofan ; Liu, Xunan ; Liu, Yang ; Dong, Jin ; Zheng, Zhiming</creatorcontrib><description>The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money laundering, are rampant in the blockchain ecosystem and seriously threaten its integrity and security. In this paper, we propose a novel double graph-based Ethereum account de-anonymization inference method, dubbed DBG4ETH, which aims to capture the behavioral patterns of accounts comprehensively and has more robust analytical and judgment capabilities for current complex and continuously generated transaction behaviors. Specifically, we first construct a global static graph to build complex interactions between the various account nodes for all transaction data. Then, we also construct a local dynamic graph to learn about the gradual evolution of transactions over different periods. Different graphs focus on information from different perspectives, and features of global and local, static and dynamic transaction graphs are available through DBG4ETH. In addition, we propose an adaptive confidence calibration method to predict the results by feeding the calibrated weighted prediction values into the classifier. Experimental results show that DBG4ETH achieves state-of-the-art results in the account identification task, improving the F1-score by at least 3.75% and up to 40.52% compared to processing each graph type individually and outperforming similar account identity inference methods by 5.23% to 12.91%.</description><identifier>DOI: 10.48550/arxiv.2411.18875</identifier><language>eng</language><subject>Computer Science - Social and Information Networks</subject><creationdate>2024-11</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2411.18875$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2411.18875$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Miao, Shuyi</creatorcontrib><creatorcontrib>Qiu, Wangjie</creatorcontrib><creatorcontrib>Zheng, Hongwei</creatorcontrib><creatorcontrib>Zhang, Qinnan</creatorcontrib><creatorcontrib>Tu, Xiaofan</creatorcontrib><creatorcontrib>Liu, Xunan</creatorcontrib><creatorcontrib>Liu, Yang</creatorcontrib><creatorcontrib>Dong, Jin</creatorcontrib><creatorcontrib>Zheng, Zhiming</creatorcontrib><title>Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum</title><description>The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money laundering, are rampant in the blockchain ecosystem and seriously threaten its integrity and security. In this paper, we propose a novel double graph-based Ethereum account de-anonymization inference method, dubbed DBG4ETH, which aims to capture the behavioral patterns of accounts comprehensively and has more robust analytical and judgment capabilities for current complex and continuously generated transaction behaviors. Specifically, we first construct a global static graph to build complex interactions between the various account nodes for all transaction data. Then, we also construct a local dynamic graph to learn about the gradual evolution of transactions over different periods. Different graphs focus on information from different perspectives, and features of global and local, static and dynamic transaction graphs are available through DBG4ETH. In addition, we propose an adaptive confidence calibration method to predict the results by feeding the calibrated weighted prediction values into the classifier. Experimental results show that DBG4ETH achieves state-of-the-art results in the account identification task, improving the F1-score by at least 3.75% and up to 40.52% compared to processing each graph type individually and outperforming similar account identity inference methods by 5.23% to 12.91%.</description><subject>Computer Science - Social and Information Networks</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjE01DO0sDA35WQI8c7LL1eIzC8tUnBMTs4vzSuxUnDJL03KSVVwL0osyFDwzEtLLUrNS07VTUosTk2BqVJwSdVNzMvPq8zNrEosyczPUwAi15IMoNrSXB4G1rTEnOJUXijNzSDv5hri7KELtj--oCgzN7GoMh7kjniwO4wJqwAAzFs9ww</recordid><startdate>20241127</startdate><enddate>20241127</enddate><creator>Miao, Shuyi</creator><creator>Qiu, Wangjie</creator><creator>Zheng, Hongwei</creator><creator>Zhang, Qinnan</creator><creator>Tu, Xiaofan</creator><creator>Liu, Xunan</creator><creator>Liu, Yang</creator><creator>Dong, Jin</creator><creator>Zheng, Zhiming</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20241127</creationdate><title>Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum</title><author>Miao, Shuyi ; Qiu, Wangjie ; Zheng, Hongwei ; Zhang, Qinnan ; Tu, Xiaofan ; Liu, Xunan ; Liu, Yang ; Dong, Jin ; Zheng, Zhiming</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2411_188753</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Social and Information Networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Miao, Shuyi</creatorcontrib><creatorcontrib>Qiu, Wangjie</creatorcontrib><creatorcontrib>Zheng, Hongwei</creatorcontrib><creatorcontrib>Zhang, Qinnan</creatorcontrib><creatorcontrib>Tu, Xiaofan</creatorcontrib><creatorcontrib>Liu, Xunan</creatorcontrib><creatorcontrib>Liu, Yang</creatorcontrib><creatorcontrib>Dong, Jin</creatorcontrib><creatorcontrib>Zheng, Zhiming</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Miao, Shuyi</au><au>Qiu, Wangjie</au><au>Zheng, Hongwei</au><au>Zhang, Qinnan</au><au>Tu, Xiaofan</au><au>Liu, Xunan</au><au>Liu, Yang</au><au>Dong, Jin</au><au>Zheng, Zhiming</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum</atitle><date>2024-11-27</date><risdate>2024</risdate><abstract>The scaled Web 3.0 digital economy, represented by decentralized finance (DeFi), has sparked increasing interest in the past few years, which usually relies on blockchain for token transfer and diverse transaction logic. However, illegal behaviors, such as financial fraud, hacker attacks, and money laundering, are rampant in the blockchain ecosystem and seriously threaten its integrity and security. In this paper, we propose a novel double graph-based Ethereum account de-anonymization inference method, dubbed DBG4ETH, which aims to capture the behavioral patterns of accounts comprehensively and has more robust analytical and judgment capabilities for current complex and continuously generated transaction behaviors. Specifically, we first construct a global static graph to build complex interactions between the various account nodes for all transaction data. Then, we also construct a local dynamic graph to learn about the gradual evolution of transactions over different periods. Different graphs focus on information from different perspectives, and features of global and local, static and dynamic transaction graphs are available through DBG4ETH. In addition, we propose an adaptive confidence calibration method to predict the results by feeding the calibrated weighted prediction values into the classifier. Experimental results show that DBG4ETH achieves state-of-the-art results in the account identification task, improving the F1-score by at least 3.75% and up to 40.52% compared to processing each graph type individually and outperforming similar account identity inference methods by 5.23% to 12.91%.</abstract><doi>10.48550/arxiv.2411.18875</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2411.18875
ispartof
issn
language eng
recordid cdi_arxiv_primary_2411_18875
source arXiv.org
subjects Computer Science - Social and Information Networks
title Know Your Account: Double Graph Inference-based Account De-anonymization on Ethereum
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T11%3A48%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Know%20Your%20Account:%20Double%20Graph%20Inference-based%20Account%20De-anonymization%20on%20Ethereum&rft.au=Miao,%20Shuyi&rft.date=2024-11-27&rft_id=info:doi/10.48550/arxiv.2411.18875&rft_dat=%3Carxiv_GOX%3E2411_18875%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true