Detecting Anomalous Cryptocurrency Transactions: an AML/CFT Application of Machine Learning-based Forensics

In shaping the Internet of Money (IoM), the application of blockchain and distributed ledger technologies (DLTs) to the financial sector triggered regulatory concerns. Notably, while the user anonymity enabled in this field may safeguard privacy, data protection and other civil liberties, lack of identifiability hinders accountability, investigation and enforcement. This challenges the framework to combat money laundering and the financing of terrorism and proliferation (AML/CFT). As both law enforcement agencies and the private sector apply forensics to track currency across blockchain ecosystems, this paper focuses on the growing relevance of these techniques. In particular, this work offers IoM-specific insights into the application of methods of machine learning and network and transaction graph analysis. Namely, it analyzes a real-world dataset of Bitcoin transactions represented as a directed graph network through various machine learning techniques. The modeling of blockchain transactions as a complex network suggests that the use of data analysis methods in machine learning, specifically thought for graphs, can aid transaction classification and help identify illicit fund transfers. Indeed, this work shows that the neural network types known as Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT) are a promising solution for AML/CFT compliance. Notably, in this AML/CFT application scenario GCN outperform other classic machine learning approaches.