构建可生成逼真洗钱交易的多智能体框架，解决数据匮乏难题。
AMLNet: A Knowledge-Based Multi-Agent Framework to Generate and Detect Realistic Money Laundering Transactions
- 基于规则的多智能体生成交易，模拟放置、清洗、融合等阶段。
- 生成超百万条合成交易，检测模型F1达0.90，适应外部数据集。
- 支持监管合规评估，适合金融安全与反洗钱研究者使用。
反洗钱（AML）研究受限于缺乏公开可共享且符合监管要求的交易数据集。本文提出AMLNet，一种基于知识的多智能体框架，包含两个协同单元：一个具备监管意识的交易生成器和一个集成检测管道。生成器创建了1,090,173条合成交易（约0.16%为洗钱阳性），覆盖核心洗钱阶段（放置、清洗、融合）及高级模式（如拆分、自适应阈值行为）。监管对齐度达75%（基于AUSTRAC规则覆盖率），综合技术真实度得分为0.75（涵盖时间、结构与行为维度）。检测集成模型在AMLNet内部测试集上达到F1=0.90（精确率0.84，召回率0.97），并可适配外部SynthAML数据集，表明架构具备跨生成范式的泛化能力。我们提供多维评估（监管、时间、网络、行为），并发布数据集（版本1.0，https://doi.org/10.5281/zenodo.16736515），以推动可复现且注重监管的反洗钱实验。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。