TMAS:A transaction misbehavior analysis scheme for blockchain  

作　　者：Shiyong Huang Xiaohan Hao Yani Sun Chenhuang Wu Huimin Li Wei Ren Kim-Kwang Raymond Choo 

机构地区：[1]School of Computer Science,China University of Geosciences,Wuhan,430074,China [2]Artificial Intelligence Thrust,Information Hub,Hong Kong University of Science and Technology,Guangzhou,511400,China [3]Yunnan Key Laboratory of Blockchain Application Technology,Yunnan Innovation Institute of Beihang University,Kunming,650233,China [4]Fujian Key Laboratory of Financial Information Processing,Putian University,Putian,351100,China [5]Department of Information Systems and Cyber Security,University of Texas at San Antonio,San Antonio,TX 78249-0631,USA

出　　处：《Blockchain(Research and Applications)》2024年第3期42-52,共11页区块链研究（英文）

基　　金：supported by the Fujian Key Labo-ratory of Financial Information Processing(Putian University)(No.JXC202304);Yunnan Key Laboratory of Block-chain Application Tech-nology(No.202305AG340008);the Opening Project of Nanchang In-novation Institute,Peking University(No.NCII2022A02);Science and Technology Project of Putian City(No.2021R4001-10).The work of K.-K.R.Choo was supported only by the Cloud Technology Endowed Professorship.

摘　　要：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).

关 键 词：Blockchain Anti-money laundering Bitcoin Cyptocurrency 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]