基于启发式的比特币地址聚类方法  

Heuristic Approaches Based Clustering of Bitcoin Addresses

作　　者：毛洪亮 吴震[1] 贺敏[1] 唐积强[1] 沈蒙[2] MAO Hong-liang;WU Zhen;HE Min;TANG Ji-qiang;SHEN Meng(National Computer Network Emergency Response Technical Team/Coordination Center of China, Beijing 100029, China;Department of Computer Science, Beijing Institute of Technology, Beijing 100081, China)

机构地区：[1]国家计算机网络应急技术处理协调中心,北京100029 [2]北京理工大学计算机学院,北京100081

出　　处：《北京邮电大学学报》2018年第2期27-31,共5页Journal of Beijing University of Posts and Telecommunications

摘　　要：针对比特币这种新型的数字货币,通过分析其交易规律和交易地址关系,综合多个交易聚类特征,提出一种基于启发式条件的聚类方法,能够对匿名比特币地址进行相关性聚类,从而发现被同一用户团体控制的地址群,有助于分析用户的交易特征,推测用户的真实身份.设计了具体的聚类方案,分析了迭代次数对聚类效果和代价的影响.大量的实验分析结果验证了该方法的准确性和全面性.Because of anonymity of Bitcoin accounts,Bitcoin may be popular in some illegal trades and black market,such as the Silk Road. The author proposed an improved heuristic approaches-based method to cluster Bitcoin addresses and identify different addresses controlled by the same user. Three heuristic evidences were employed jointly. Through an elaborately designed experimental analysis,the precision and recall of the proposed method was verified. Furthermore,the efficiency with different iterations was analyzed,which can provide guidance in designing efficient clustering algorithm.

关 键 词：比特币 启发式 聚类 

分 类 号：TN911.4[电子电信—通信与信息系统]