From asset flow to status, action, and intention discovery: Early malice detection in cryptocurrency

• Main Authors: CHENG, Ling, ZHU, Feida, WANG, Yong, LIANG, Ruicheng, LIU, Huiwen
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2024
• 主題: Blockchain; Cryptocurrency; data mining; fraud detection; early detection; Databases and Information Systems; Information Security
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/9426; https://ink.library.smu.edu.sg/context/sis_research/article/10426/viewcontent/3626102_pvoa_cc_by.pdf
• 機構: Singapore Management University

Cryptocurrency has been subject to illicit activities probably more often than traditional financial assets due to the pseudo-anonymous nature of its transacting entities. An ideal detection model is expected to achieve all three critical properties of early detection, good interpretability, and versatility for various illicit activities. However, existing solutions cannot meet all these requirements, as most of them heavily rely on deep learning without interpretability and are only available for retrospective analysis of a specific illicit type. To tackle all these challenges, we propose Intention Monitor for early malice detection in Bitcoin, where the on-chain record data for a certain address are much scarcer than other cryptocurrency platforms.We first define asset transfer paths with the Decision Tree based feature Selection and Complement to build different feature sets for different malice types. Then, the Status/Action Proposal module and the Intention-VAE module generate the status, action, intent-snippet, and hidden intent-snippet embedding. With all these modules, our model is highly interpretable and can detect various illegal activities. Moreover, well-designed loss functions further enhance the prediction speed and the model’s interpretability. Extensive experiments on three real-world datasets demonstrate that our proposed algorithm outperforms the state-of-the-art methods. Furthermore, additional case studies justify that our model not only explains existing illicit patterns but also can find new suspicious characters.