Leveraging Subgraph Structure for Exploration and Analysis of Bitcoin Address

Abstract

The growing acceptance and popularity of cryptocurrencies have boosted the digital financial markets, which have also increased crime risk due to their anonymity and decentralization. Appropriately monitoring decentralized cryptocurrency, particularly Bitcoin, can prevent participants from financial loss and benefit the community. Therefore, in this paper, we build the first Bitcoin address subgraph dataset called BASD-8, which contains 3,830 labeled Bitcoin address subgraphs, and we study the structural characteristics of these subgraphs, aiming at identifying eight common types of Bitcoin addresses to distinguish between normal and abnormal addresses. Three methods are utilized to exploit subgraph patterns: complex network, machine learning, and empirical analysis. Specifically, we calculate ten vital metrics of subgraphs as features to train address classifiers using basic machine learning models. Also, a graph neural network model is trained as a graph-level classifier, and the experimental results with the best f1-score of 91.35% illustrate the effectiveness of our dataset and study methods. Furthermore, we conduct a detailed empirical pattern analysis combining the subgraph structures and the definitions of each category of Bitcoin addresses.