Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics

Abstract

Anti-money laundering (AML) regulations play a critical role in safeguarding financial systems, but bear high costs for institutions and drive financial exclusion for those on the socioeconomic and international margins. The advent of cryptocurrency has introduced an intriguing paradox: pseudonymity allows criminals to hide in plain sight, but open data gives more power to investigators and enables the crowdsourcing of forensic analysis. Meanwhile advances in learning algorithms show great promise for the AML toolkit. In this workshop tutorial, we motivate the opportunity to reconcile the cause of safety with that of financial inclusion. We contribute the Elliptic Data Set, a time series graph of over 200K Bitcoin transactions (nodes), 234K directed payment flows (edges), and 166 node features, including ones based on non-public data; to our knowledge, this is the largest labelled transaction data set publicly available in any cryptocurrency. We share results from a binary classification task predicting illicit transactions using variations of Logistic Regression (LR), Random Forest (RF), Multilayer Perceptrons (MLP), and Graph Convolutional Networks (GCN), with GCN being of special interest as an emergent new method for capturing relational information. The results show the superiority of Random Forest (RF), but also invite algorithmic work to combine the respective powers of RF and graph methods. Lastly, we consider visualization for analysis and explainability, which is difficult given the size and dynamism of real-world transaction graphs, and we offer a simple prototype capable of navigating the graph and observing model performance on illicit activity over time. With this tutorial and data set, we hope to a) invite feedback in support of our ongoing inquiry, and b) inspire others to work on this societally important challenge.

7 pages, Tutorial in the Anomaly Detection in Finance Workshop at the 25th SIGKDD Conference on Knowledge Discovery and Data Mining

References in corpus (5)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Scalable Graph Learning for Anti-Money Laundering: A First Look

Cited by in corpus (25)

• Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
• Adversarial Attack and Defense on Graph Data: A Survey
• Detecting Mixing Services via Mining Bitcoin Transaction Network with Hybrid Motifs
• Identity Inference on Blockchain using Graph Neural Network
• Characterizing and Detecting Money Laundering Activities on the Bitcoin Network
• Z-GCNETs: Time Zigzags at Graph Convolutional Networks for Time Series Forecasting
• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
• Graph Mining for Cybersecurity: A Survey
• Digital Forensics vs. Anti-Digital Forensics: Techniques, Limitations and Recommendations
• Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networks
• Explainability-based Backdoor Attacks Against Graph Neural Networks
• Backdoor Attacks to Graph Neural Networks
• Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Review
• Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification
• Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks
• Towards Artificial Intelligence Enabled Financial Crime Detection
• Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
• Node Copying: A Random Graph Model for Effective Graph Sampling
• GuiltyWalker: Distance to illicit nodes in the Bitcoin network
• Seven challenges for harmonizing explainability requirements
• Insights into Fairness through Trust: Multi-scale Trust Quantification for Financial Deep Learning
• How to Not Get Caught When You Launder Money on Blockchain?
• Watermarking Graph Neural Networks based on Backdoor Attacks
• Generating a Doppelganger Graph: Resembling but Distinct