TMAS: A transaction misbehavior analysis scheme for blockchain

Abstract

Blockchain-based cryptocurrencies, such as Bitcoins, are increasingly popular. However, the decentralized and anonymous nature of these currencies can also be (ab)used for nefarious activities such as money laundering, thus reinforcing the importance of designing tools to effectively detect malicious transaction misbehaviors. In this paper, we propose TMAS, a transaction misbehavior analysis scheme for blockchain-based cryptocurrencies. Specifically, the proposed system includes ten features in the transaction graph, two heuristic money laundering models, and an analysis method for account linkage, which identifies accounts that are distinct but controlled by an identical entity. To evaluate the effectiveness of our proposed indicators and models, we analyze 100 million transactions and compute transaction features, and are able to identify a number of suspicious accounts. Moreover, the proposed methods can be applied to other cryptocurrencies, such as token-based cryptocurrencies (e.g., Bitcoins) and account-based cryptocurrencies (e.g., Ethereum).