基于机器学习的比特币去匿名化方法研究

doi:10.19678/j.issn.1000-3428.0060406

计算机工程 ›› 2021, Vol. 47 ›› Issue (12): 47-53. doi: 10.19678/j.issn.1000-3428.0060406

基于机器学习的比特币去匿名化方法研究

郭文生^1,2, 杨霞^1,2, 冯志淇², 张露晨³, 杨菁林³

1. 电子科技大学信息与软件工程学院, 成都 610000;
2. 成都链安科技有限公司, 成都 610000;
3. 国家互联网应急中心, 北京 100000

收稿日期:2020-12-28 修回日期:2021-03-22 发布日期:2021-05-12
作者简介:郭文生(1976-),男,副教授、博士,主研方向为区块链安全、人工智能;杨霞,副教授、博士;冯志淇,高级工程师、硕士;张露晨,副研究员、博士;杨菁林,工程师、硕士。
基金资助:
国家242信息安全专项（2020A028）；四川省科技计划项目（2020YFG0481）。

Research of De-Anonymizing Method Based on Machine Learning for Bitcoin

GUO Wensheng^1,2, YANG Xia^1,2, FENG Zhiqi², ZHANG Luchen³, YANG Jinglin³

1. School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610000, China;
2. Chengdu LianAn Technology Co., Ltd., Chengdu 610000, China;
3. National Internet Emergency Center, Beijing 100000, China

Received:2020-12-28 Revised:2021-03-22 Published:2021-05-12

摘要/Abstract

摘要： 比特币是一种去中心化的匿名加密货币，是目前使用最广泛的数字资产之一，具有匿名性、无主权、无地域限制的特点，匿名性的特性也使得比特币被广泛应用于各种犯罪活动。为实现比特币的去匿名化，提出一种联合特征构造方法并构建随机森林与Softmax相结合的分类模型。为更好地区分不同类型比特币的交易行为，引用交易实体的概念，按照联合特征构造方法分别从地址、实体与交易网络结构3个方面在海量的交易数据中构造特征，并将其整合成联合特征向量。实验结果表明，该实体分类模型的类别识别精确率超过0.92，其能够有效提升执法机构对虚拟货币犯罪行为的调查取证能力。

关键词: 比特币, 去匿名化, 犯罪活动, 交易实体, 联合特征, 随机森林

Abstract: Bitcoin is one of the most widely used digital assets.It is a kind of decentralized anonymous cryptocurrency, and has no sovereignty or geographical restrictions.However, its anonymity makes it abused in illegal activities.To realize de-anonymization for Bitcoin, a classification model combining Random Forest(RF) and Softmax is proposed along with a joint features construction method.To distinguish the transactions of different kinds of Bitcoin, the concept of entity is introduced.On this basis, the joint feature construction method is used to construct features in massive transaction data from the aspects of address, entity and transaction network, and the constructed features are integrated into a joint feature vector.The experimental results show that the proposed entity classification model displays a classification accuracy of over 0.92.It can effectively assist law-enforcement agencies in investigating and collecting evidence of illegal activities involving virtual currency.

Key words: Bitcoin, de-anonymization, illegal activity, trading entity, joint feature, Random Forest(RF)

中图分类号:

TP391

郭文生, 杨霞, 冯志淇, 张露晨, 杨菁林. 基于机器学习的比特币去匿名化方法研究[J]. 计算机工程, 2021, 47(12): 47-53.

GUO Wensheng, YANG Xia, FENG Zhiqi, ZHANG Luchen, YANG Jinglin. Research of De-Anonymizing Method Based on Machine Learning for Bitcoin[J]. Computer Engineering, 2021, 47(12): 47-53.

http://www.ecice06.com/CN/Y2021/V47/I12/47

图/表 9

20211213181508

20211213181511

20211213181514

20211213181517

20211213181520

20211213181524

20211213181527

20211213181531

20211213181534

参考文献

[1] ADAMS C.Learning the lessons of WannaCry[J].Computer Fraud & Security, 2018(9):6-9.
[2] PHAM T, LEE S.Anomaly detection in Bitcoin network using unsupervised learning methods[EB/OL].[2020-11-05].https://arxiv.org/pdf/1611.03941v2.pdf.
[3] RACHANA K, MONICA C.Anomaly detection in blockchain using clustering protocol[J].International Journal of Engineering Research in Computer Science and Engineering, 2017, 4(12):12-23.
[4] THAI P, STEVEN L.Anomaly detection in the Bitcoin system-a network perspective[EB/OL].[2020-11-05].https://arxiv.org/pdf/1611.03942v2.pdf.
[5] WU J, LIU J, CHEN W, et al.Detecting mixing services via mining Bitcoin transaction network with hybrid motifs[EB/OL].[2020-11-05].https://arxiv.org/pdf/2001.05233.pdf.
[6] WEBER M, DOMENICONI G, CHEN J, et al.Anti-money laundering in Bitcoin:experimenting with graph convolutional networks for financial forensics[EB/OL].[2020-11-05].https://arxiv.org/pdf/1908.02591v1.pdf.
[7] HU Y, SENEVIRATNE S, THILAKARATHNA K, et al.Characterizing and detecting money laundering activities on the Bitcoin network[EB/OL].[2020-11-05].https://arxiv.org/pdf/1912.12060v1.pdf.
[8] TOYODA K, OHTSUKI T, MATHIOPOULOS P T.Multi-class Bitcoin-enabled service identification based on transaction history summarization[C]//Proceedings of IEEE International Conference on Blockchain.Washington D.C., USA:IEEE Press, 2018:1153-1160.
[9] NERURKAR P, BHIRUD S, PATEL D, et al.Supervised learning model for identifying illegal activities in Bitcoin[J].Applied Intelligence, 2020, 6:1-20.
[10] PRANAV N, YANN B, ROMARIC L, et al.Detecting illicit entities in Bitcoin using supervised learning of ensemble decision trees[EB/OL].[2020-11-05].https://hal-imt-atlantique.archives-ouvertes.fr/hal-02952081/document.
[11] MASSIMO B, BARBARA P, SERGIO S.Data mining for detecting Bitcoin ponzi schemes[C]//Proceeding of Crypto Valley Conference on Blockchain Technology.Washington D.C., USA:IEEE Press, 2018:75-84.
[12] YIN H H S, LANGENHELDT K, HARLEV M, et al.Regulating cryptocurrencies:a supervised machine learning approach to de-anonymizing the Bitcoin blockchain[J].Journal of Management Information Systems, 2019, 36(1):37-73.
[13] HARLEV M A, YIN H S, LANGENHELDT K C, et al.Breaking bad:de-anonymising entity types on the Bitcoin blockchain using supervised machine learning[EB/OL].[2020-11-05].https://scholarspace.manoa.hawaii.edu/bitstream/10125/50331/1/paper0444.pdf.
[14] RANSHOUS S, JOSLYN C A, KREYLING S, et al.Exchange pattern mining in the Bitcoin transaction directed hypergraph[C]//Proceedings of International Conference on Financial Cryptography and Data Security.Berlin, Germany:Springer, 2017:248-263.
[15] JOURDAN M, BLANDIN S, WYNTER L, et al.Characterizing entities in the Bitcoin blockchain[EB/OL].[2020-11-05].https://arxiv.org/pdf/1810.11956.pdf.
[16] REID F, HARRIGAN M.An analysis of anonymity in the Bitcoin system[EB/OL].[2020-11-05].https://arxiv.org/PS_cache/arxiv/pdf/1107/1107.4524v1.pdf.
[17] JAWAHERI H A, SABAH M A, BOSHMAF Y, et al.When a small leak sinks a great ship:deanonymizing tor hidden service users through Bitcoin transactions analysis[EB/OL].[2020-11-05].https://arxiv.org/pdf/1801.07501.pdf.
[18] RON D, SHAMIR A.Quantitative analysis of the full Bitcoin transaction graph[C]//Proceedings of International Conference on Financial Cryptography and Data Security.Berlin, Germany:Springer, 2013:6-24.
[19] MILO R, SHEN-ORR S, ITZKOVITZ S, et al.Network motifs:simple building blocks of complex networks[J].Science, 2002, 298(5594):824-827.
[20] JOURDAN M, BLANDIN S, WYNTER L, et al.A probabilistic model of the Bitcoin blockchain[EB/OL].[2020-11-05].https://arxiv.org/pdf/1812.05451.pdf.
[21] HE X R, PAN J F, OU J, et al.Practical lessons from predicting clicks on ads at Facebook[EB/OL].[2020-11-05].http://www0.cs.ucl.ac.uk/staff/w.zhang/pubapers/adkdd_2014_camera_ready_junfeng.pdf.

选择文件类型/文献管理软件名称

选择包含的内容

基于机器学习的比特币去匿名化方法研究

Research of De-Anonymizing Method Based on Machine Learning for Bitcoin

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	余长宏, 陆雅, 王海鑫, 高明. 基于滑动时间窗的物联网设备流量分类算法[J]. 计算机工程, 2023, 49(7): 259-268.
[2]	俞莎莎, 牛保宁. 基于交易不可信度的比特币非法交易检测[J]. 计算机工程, 2022, 48(8): 166-172.
[3]	王劲松, 赵述佳, 赵泽宁, 张洪玮. 基于交易网络的公有链用户识别方法[J]. 计算机工程, 2022, 48(8): 30-36.
[4]	杨志勇, 王俊杰, 金磊. 基于SE-CNN的人体摔倒检测方法[J]. 计算机工程, 2022, 48(6): 270-277.
[5]	常硕, 张彦春. 基于袋外预测和扩展空间的随机森林改进算法[J]. 计算机工程, 2022, 48(3): 1-9.
[6]	郑小敏, 李翔宇. 随机森林手势识别算法的高效嵌入式软件实现[J]. 计算机工程, 2021, 47(7): 218-225.
[7]	郝占军, 张岱阳, 党小超, 段渝. 基于信道状态信息的非接触式人员动作识别方法[J]. 计算机工程, 2021, 47(6): 172-181.
[8]	吕芳, 汤丰赫, 黄俊恒, 王佰玲. 面向非平衡数据集的金融欺诈账户检测研究[J]. 计算机工程, 2021, 47(6): 312-320.
[9]	康璐璐, 范兴容, 王茜竹, 杨晓雅, 明蕊. 基于特征组分层与半监督学习的鼠标轨迹识别[J]. 计算机工程, 2021, 47(4): 277-284.
[10]	张玲, 张建伟, 桑永宣, 王博, 侯泽翔. 基于随机森林与人工免疫的入侵检测算法[J]. 计算机工程, 2020, 46(8): 146-152.
[11]	王劲松, 吕志梅, 赵泽宁, 张洪玮. 面向区块链交易可视分析的地址增量聚类方法[J]. 计算机工程, 2020, 46(8): 14-20.
[12]	丁龙斌, 伍忠东, 苏佳丽. 基于集成深度森林的入侵检测方法[J]. 计算机工程, 2020, 46(3): 144-150.
[13]	谢坤, 容钰添, 胡奉平, 陈桓, 姚小龙. 基于数据集成的随机森林算法[J]. 计算机工程, 2020, 46(12): 290-298.
[14]	舒斐, 陈涛, 王斌, 杨慧婷, 李明轩. 一种基于DBN-RF的电网工控系统异常识别方法[J]. 计算机工程, 2020, 46(11): 35-41.
[15]	李远航, 陈先来, 刘莉, 安莹, 李忠民. 面向差分隐私保护的随机森林算法[J]. 计算机工程, 2020, 46(1): 93-101.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于机器学习的比特币去匿名化方法研究

Research of De-Anonymizing Method Based on Machine Learning for Bitcoin

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价