[1]张梦楠,吴礼发.基于交易网络特征增强的比特币异常地址识别[J].计算机技术与发展,2023,33(09):8-15.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 002]
 ZHANG Meng-nan,WU Li-fa.Abnormal Address Recognition of Bitcoin Based on Enhanced Transaction Network Features[J].,2023,33(09):8-15.[doi:10. 3969 / j. issn. 1673-629X. 2023. 09. 002]
点击复制

基于交易网络特征增强的比特币异常地址识别()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年09期
页码:
8-15
栏目:
分布与并行计算
出版日期:
2023-09-10

文章信息/Info

Title:
Abnormal Address Recognition of Bitcoin Based on Enhanced Transaction Network Features
文章编号:
1673-629X(2023)09-0008-08
作者:
张梦楠吴礼发
南京邮电大学 网络空间安全学院,江苏 南京 210023
Author(s):
ZHANG Meng-nanWU Li-fa
School of Cyberspace Security,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
关键词:
比特币异常地址识别机器学习特征提取网络科学
Keywords:
Bitcoinabnormal address recognitionmachine learningfeature extractionnetwork science
分类号:
TP309
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 09. 002
摘要:
比特币由于其便捷性、匿名性、全球性、高流动性的特点,为犯罪分子使用其作为价值传递的媒介从事犯罪活动提供了理想的工具,产生大量利用比特币进行勒索、洗钱、非法毒品、武器交易等异常交易问题。 传统基于有监督的异常地址识别方法由于交易信息单一,不能全面和准确地反映地址间的关系,异常地址识别率较低。 该文提出了一种基于交易网络特征增强的比特币异常地址识别方法。 该方法将比特币交易数据转化为复杂网络,并提出一种基于改进的 PageRank的节点重要性特征构造方法,根据比特币交易特点,引入比特币交易额度和频率相关性得到新的 PageRank 值并加入特征集。 通过对不同的机器学习方法进行比较以获得最佳的预测模型,提升检测模型的分类效果。 与传统的检测方法相比,结合网络信息的模型具有更好的检测性能,其中极限梯度提升树( XGBoost) 分类器效果最好,F1 分数由原来的 0. 83 提升至 0. 94,AUC 值由原来的 0. 88 提升至 0. 95。
Abstract:
Because of its convenience,anonymity,globality and high mobility,Bitcoin provides an ideal tool for criminals to use it as amedium of value transmission to engage in criminal activities,resulting in a large number of abnormal transactions such as extortion,money laundering,illegal drugs and weapons trading. The traditional method?
of anomaly address recognition based on supervision cannotfully and accurately reflect the relationship between addresses due to the single transaction information, so the recognition rate of anomalyaddress is low.?
Therefore,we propose a Bitcoin anomaly address recognition method based on transaction network feature enhancement.This method converts Bitcoin transaction data into a complex network and extracts network features,and proposes a node importancefeature construction method based on improved PageRank. According to Bitcoin transaction features,the Bitcoin transaction quota andfrequency correlation are introduced to obtain new PR values and add them to the feature collection. By comparing different machinelearning methods,we can get the best prediction model and improve the classification effect of the detection model. Compared with thetraditional detection methods, the model combined with network information has a better detection performance. Among them, theXGBoost classifier has the best performance. The F1 score increases from 0. 83 to 0. 94,and the AUC value increases from 0. 88 to 0. 95.

相似文献/References:

[1]吕楠.Bitcoin合作式矿区挖矿研究[J].计算机技术与发展,2014,24(02):39.
 Lü Nan.Research on Bitcoin Cooperative Mining Area[J].,2014,24(09):39.

更新日期/Last Update: 2023-09-10