GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering

2025-06-04

AI Summary

Detecting “smurfing” (structuring) in money laundering remains challenging due to low interpretability, poor integration with existing anti-money laundering (AML) workflows, and difficulty in identifying subtle, fragmented transaction patterns. Method: This paper proposes an interpretable graph analytics framework based on second-order transaction network structure. It models local topology via second-order adjacency matrices, extracts structural features, and integrates them into a lightweight, single-metric graph risk scorer using tree-based models and neighbor-risk aggregation—without requiring graph embedding. Contribution/Results: The approach is the first to achieve auditable, high-efficiency, and high-accuracy unified modeling without graph embedding. It balances computational performance (low latency), operational transparency (end-to-end traceability), and detection capability. Evaluated on large-scale synthetic data and open financial networks, it significantly outperforms state-of-the-art methods, achieving high detection accuracy using only basic topological information.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

Money laundering poses a significant challenge as it is estimated to account for 2%-5% of the global GDP. This has compelled regulators to impose stringent controls on financial institutions. One prominent laundering method for evading these controls, called smurfing, involves breaking up large transactions into smaller amounts. Given the complexity of smurfing schemes, which involve multiple transactions distributed among diverse parties, network analytics has become an important anti-money laundering tool. However, recent advances have focused predominantly on black-box network embedding methods, which has hindered their adoption in businesses. In this paper, we introduce GARG-AML, a novel graph-based method that quantifies smurfing risk through a single interpretable metric derived from the structure of the second-order transaction network of each individual node in the network. Unlike traditional methods, GARG-AML strikes an effective balance among computational efficiency, detection power and transparency, which enables its integration into existing AML workflows. To enhance its capabilities, we combine the GARG-AML score calculation with different tree-based methods and also incorporate the scores of the node's neighbours. An experimental evaluation on large-scale synthetic and open-source networks demonstrate that the GARG-AML outperforms the current state-of-the-art smurfing detection methods. By leveraging only the adjacency matrix of the second-order neighbourhood and basic network features, this work highlights the potential of fundamental network properties towards advancing fraud detection.

Problem

• Detecting smurfing in money laundering using graph analytics
• Balancing efficiency and interpretability in AML risk quantification
• Improving fraud detection with second-order transaction network analysis

Innovation

• Graph-based method for smurfing risk quantification
• Interpretable metric from second-order transaction network
• Combines GARG-AML with tree-based methods