【Author】
Lin, Yu-Jing; Wu, Po-Wei; Hsu, Cheng-Han; Tu, I-Ping; Liao, Shih-wei
【Source】2019 IEEE INTERNATIONAL CONFERENCE ON BLOCKCHAIN AND CRYPTOCURRENCY (ICBC)
【Abstract】Bitcoin is a cryptocurrency that features a distributed, decentralized and trustworthy mechanism, which has made Bitcoin a popular global transaction platform. The transaction efficiency among nations and the privacy benefiting from address anonymity of the Bitcoin network have attracted many activities such as payments, investments, gambling, and even money laundering in the past decade. Unfortunately, some criminal behaviors which took advantage of this platform were not identified. This has discouraged many governments to support cryptocurrency. Thus, the capability to identify criminal addresses becomes an important issue in the cryptocurrency network. In this paper, we propose new features in addition to those commonly used in the literature to build a classification model for detecting abnormality of Bitcoin network addresses. These features include various high orders of moments of transaction time (represented by block height) which summarizes the transaction history in an efficient way. The extracted features are trained by supervised machine learning methods on a labeling category data set. The experimental evaluation shows that these features have improved the performance of Bitcoin address classification significantly. We evaluate the results under eight classifiers and achieve the highest Micro-F1 / Macro-F1 of 87% / 86% with LightGBM.
【Keywords】bitcoin; blockchain; classification; moments; transaction history summarization
【摘要】比特币是一种以分布式、去中心化和可信赖机制为特点的加密货币，这使得比特币成为一个受欢迎的全球交易平台。在过去的十年中，比特币网络的交易效率和地址匿名带来的隐私，吸引了支付、投资、赌博甚至洗钱等许多活动。不幸的是，一些利用该平台的犯罪行为并没有被发现。这使得许多政府不愿支持加密货币。因此，识别犯罪地址的能力成为加密货币网络中的一个重要问题。在本文中，我们在文献中常用特征的基础上，提出了新的特征来构建一个检测比特币网络地址异常的分类模型。这些特性包括各种高阶的交易时间时刻(以块高度表示)，以有效的方式总结了交易历史。提取的特征通过监督机器学习方法在标签类别数据集上进行训练。实验结果表明，这些特征显著提高了比特币地址分类的性能。我们在8个分类器下评估了结果，并在LightGBM中获得了最高的Micro-F1 / Macro-F1，为87% / 86%。
【关键词】比特币;区块链;分类;时刻;交易历史总结
评论