The development of blockchain technology has brought prosperity to the cryptocurrency market and has made the blockchain platform a hotbed of crimes. As one of the most rampant crimes, crypto gambling has more high risk of illegal activities due to the lack of regulation. As a result, identifying crypto addresses with gambling behaviors has emerged as a significant research topic. In this work, we propose a novel detection approach based on Graph Neural Networks named CGDetector, consisting of Graph Construction, Subgraph Extractor, Statistical Feature Extraction, and Gambling Address Classification. Extensive experiments of large-scale and heterogeneous Ethereum transaction data are implemented to demonstrate that our proposed approach outperforms state-of-the-art address classifiers of traditional machine learning methods. This work makes the first attempt to detect suspicious crypto gambling addresses via Graph Neural Networks by all EVM-compatible blockchain systems, providing new insights into the field of cryptocurrency crime detection and blockchain security regulation.


Paper Number 1792; Track General; Complete Paper


When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.