Who is Who on Ethereum? Account Labeling Using Heterophilic Graph Convolutional Network

计算机科学 图形 理论计算机科学
作者
Dan Lin,Jiajing Wu,Tao Huang,Kaixin Lin,Zibin Zheng
出处
期刊:IEEE transactions on systems, man, and cybernetics [Institute of Electrical and Electronics Engineers]
卷期号:54 (3): 1541-1553 被引量:4
标识
DOI:10.1109/tsmc.2023.3329520
摘要

To combat cybercrimes and maintain financial security for the blockchain ecosystem, "know your customer" (KYC) is an essential and also challenging process due to the pseudonymity nature of blockchain technology. To unlock the potential of KYC on blockchain-based platforms like Ethereum, account labeling is a powerful means which can de-anonymize addresses by mining public transaction records. Existing studies on account labeling are mainly conducted via machine learning (ML) methods fed with hand-crafted features or graph neural networks based on the modeled transaction network. However, ML approaches based on hand-crafted features ignore the global interaction information between accounts, making it easy for criminals to evade detection. Moreover, the performance of traditional GCN methods when applied to Ethereum transaction network encounters limitations due to label sparsity, network heterophily, and large network size of the transaction network. In this article, we first analyze Ethereum accounts involved in typical businesses, in terms of both account and topological features. Then based on the analytical results, we propose a novel GCN method named know-your-customer graph convolutional network (KYC-GCN) which contains two key designs: 1) multihop aggregators and importance-based sampling are designed to tackle the dilemma between accuracy and efficiency. 2) GCN architecture is improved to explicitly capture local and more global information. Experimental results on a realistic Ethereum dataset show that the proposed KYC-GCN (90.2% accuracy, 86.2% Marco-F1) achieves state-of-the-art classification performance, and results on six benchmarks demonstrate that it yields great performance under homophily and heterophily.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
小二郎应助梦梦采纳,获得10
刚刚
Arthur完成签到,获得积分10
1秒前
小伙子发布了新的文献求助10
1秒前
iNk应助缥缈的紫文采纳,获得20
2秒前
内向的火车完成签到 ,获得积分10
3秒前
南瓜气气发布了新的文献求助30
6秒前
白金之星完成签到 ,获得积分10
6秒前
My完成签到,获得积分10
6秒前
xxx完成签到,获得积分20
7秒前
7秒前
8秒前
jesi完成签到,获得积分10
8秒前
8秒前
彩色的亦旋完成签到 ,获得积分10
11秒前
xf发布了新的文献求助10
11秒前
小猪发布了新的文献求助10
12秒前
ANN发布了新的文献求助10
13秒前
14秒前
14秒前
kunkunna完成签到,获得积分10
15秒前
15秒前
南瓜气气完成签到,获得积分10
16秒前
17秒前
17秒前
小龙虾发布了新的文献求助10
17秒前
yjjin完成签到,获得积分10
18秒前
淡然发布了新的文献求助10
19秒前
科目三应助小伙子采纳,获得10
19秒前
hkh完成签到,获得积分10
20秒前
芋圆发布了新的文献求助20
20秒前
彩色的亦旋关注了科研通微信公众号
20秒前
毛毛妈完成签到,获得积分10
21秒前
kunkunna发布了新的文献求助10
21秒前
22秒前
Legend_完成签到,获得积分10
22秒前
白水完成签到,获得积分10
23秒前
阿布发布了新的文献求助10
23秒前
香蕉觅云应助安生采纳,获得10
24秒前
lapidary发布了新的文献求助10
25秒前
安静复天完成签到,获得积分10
25秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969574
求助须知:如何正确求助?哪些是违规求助? 3514435
关于积分的说明 11173986
捐赠科研通 3249755
什么是DOI,文献DOI怎么找? 1794979
邀请新用户注册赠送积分活动 875537
科研通“疑难数据库(出版商)”最低求助积分说明 804844