基于网络表示学习的区块链异常交易检测  

Blockchain abnormal transaction detection based on network representation learning

作　　者：张晓琦 白雪 李光松[1] 王永娟 Zhang Xiaoqi;Bai Xue;Li Guangsong;Wang Yongjuan(School of Cyberspace Security,Information Engineering University,Zhengzhou 450001,China;China Institute of Marine Technology&Economy,Beijing 100081,China;Henan Key Laboratory of Network Cryptography Technology,Zhengzhou 450001,China)

机构地区：[1]信息工程大学网络空间安全学院,河南郑州450001 [2]中国船舶工业综合技术经济研究院,北京100081 [3]河南省网络密码重点实验室,河南郑州450001

出　　处：《网络安全与数据治理》2022年第10期11-20,共10页CYBER SECURITY AND DATA GOVERNANCE

基　　金：河南省重大公益专项(201300210200)。

摘　　要：由于具有巨大的流通市值、庞大的用户量和账户匿名性的特点,区块链交易频繁受到盗窃、庞氏骗局、欺诈等异常行为的威胁。针对区块链异常交易,提出一种网络表示学习模型DeepWalk-Ba用于特征提取,以比特币为例,对区块链交易的网络结构和属性进行学习,从交易的邻域结构中挖掘隐含信息作为节点特征,再使用5种有监督和1种无监督的机器学习算法进行异常检测。实验表明,有监督模型随机森林表现最好,达到了99.3%的精确率和86.4%的召回率,比使用传统的特征提取方法的异常检测模型具有更好的检测效果。Due to its characteristics of huge circulation market value,user volume and anonymity of accounts,blockchain transactions are frequently threatened by abnormal behaviours such as theft,Ponzi scheme and fraud.This paper proposed a network representation learning model DeepWalk-Ba as feature extraction method,taking bitcoin as an example,to learn the network structure and attributes of blockchain transactions,and excavate hidden information from the neighborhood structure of transactions as features.Then,5 supervised and 1 unsupervised machine learning algorithms were used for anomaly detection.The experiment indicated that the supervised model random forest performed best,with a precision of 99.3%and recall value of 86.4%.The detection effect was better than detection models using the traditional feature extraction methods.

关 键 词：区块链 异常检测 网络表示学习 随机游走 机器学习 

分 类 号：TP311.1[自动化与计算机技术—计算机软件与理论]