Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

10-2023

Abstract

Cryptocurrency’s pseudo-anonymous nature makes it vulnerable to malicious activities. However, existing deep learning solutions lack interpretability and only support retrospective analysis of specific malice types. To address these challenges, we propose Intention-Monitor for early malice detection in Bitcoin. Our model, utilizing Decision-Tree based feature Selection and Complement (DT-SC), builds different feature sets for different malice types. The Status Proposal Module (SPM) and hierarchical self-attention predictor provide real-time global status and address label predictions. A survival module determines the stopping point and proposes the status sequence (intention). Our model detects various malicious activities with strong interpretability, outperforming state-of-the-art methods in extensive experiments on three real-world datasets. It also explains existing malicious patterns and identifies new suspicious characteristics through additional case studies.

Keywords

Illicit address, Cybercrime, Early detection, Intention-aware, Bitcoin

Discipline

Databases and Information Systems | Information Security | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Honolulu, October 1-4: Proceedings

First Page

1846

Last Page

1847

ISBN

9798350337020

Identifier

10.1109/SMC53992.2023.10394086

Publisher

IEEE

City or Country

Piscataway, NJ

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/SMC53992.2023.10394086

Download

Share

COinS