AMLNet: A Knowledge-Based Multi-Agent Framework to Generate and Detect Realistic Money Laundering Transactions

2025-09-15

AI Summary

AML research has long been hindered by the scarcity of compliant, shareable real-world transaction data. To address this, we propose the first knowledge-driven multi-agent synthetic framework that integrates AUSTRAC regulatory rule awareness with collaborative detection-informed design, enabling high-fidelity generation of transactions spanning all money laundering stages and complex laundering patterns. Our method combines a rule-matching engine, temporal modeling, and multi-agent coordination to ensure regulatory alignment throughout synthesis. The framework generates 1.09 million transactions (0.16% money laundering instances), achieving 75% regulatory alignment and 0.75 technical fidelity. Downstream detection models attain an F1-score of 0.90; cross-paradigm generalizability is validated on SynthAML. The resulting dataset (v1.0) is publicly released, establishing a reproducible, regulation-compliant infrastructure for AML research.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Anti-money laundering (AML) research is constrained by the lack of publicly shareable, regulation-aligned transaction datasets. We present AMLNet, a knowledge-based multi-agent framework with two coordinated units: a regulation-aware transaction generator and an ensemble detection pipeline. The generator produces 1,090,173 synthetic transactions (approximately 0.16% laundering-positive) spanning core laundering phases (placement, layering, integration) and advanced typologies (e.g., structuring, adaptive threshold behavior). Regulatory alignment reaches 75% based on AUSTRAC rule coverage (Section 4.2), while a composite technical fidelity score of 0.75 summarizes temporal, structural, and behavioral realism components (Section 4.4). The detection ensemble achieves F1 0.90 (precision 0.84, recall 0.97) on the internal test partitions of AMLNet and adapts to the external SynthAML dataset, indicating architectural generalizability across different synthetic generation paradigms. We provide multi-dimensional evaluation (regulatory, temporal, network, behavioral) and release the dataset (Version 1.0, https://doi.org/10.5281/zenodo.16736515), to advance reproducible and regulation-conscious AML experimentation.

Problem

• Generating realistic synthetic money laundering transaction datasets
• Detecting money laundering activities with high accuracy
• Ensuring regulatory alignment in anti-money laundering research

Innovation

• Knowledge-based multi-agent framework for transactions
• Regulation-aware synthetic transaction generator
• Ensemble detection pipeline with high F1