联邦反洗钱中跨银行上下文定价
Pricing Cross-Bank Context in Federated Anti-Money Laundering
Lidia Losavio · Dario Fenoglio · Martin Gjoreski · Marc Langheinrich
中文摘要
基于图的反洗钱(AML)方法通常假设可访问包含所有账户和支付的合并交易图，但这在现实中并不存在。联邦学习提供了必要的隐私保障，但如何有效检测跨越不同图的洗钱模式仍不明确。利用端点银行已记录的交易在本地近似远程账户状态，从而在不进行额外账户特定交换的情况下实现多层图神经网络(GNN)计算。基于此基线，通过披露阶梯测试剩余上下文是否值得共享，该阶梯为每个远程账户增加两个交易计数或交易对手自身的GNN状态。在AMLworld HI-Small数据集上，针对六种GNN骨干和最多32个数据孤岛，可观察基线带来最大增益，且随着可见切片碎片化减少而保持优势；计数提供稳健修正，而精确远程状态仅在特定机制下有帮助。在受控的隐私-效用研究中，保护共享状态所需的噪声在获得有意义的隐私之前就已消除其检测价值，而计数在强隐私保护下仍保持有用。这些发现支持银行的实用规则：使用已记录的数据，并正式保护必须传输的少量数据。
关键要点
- 01现有图反洗钱方法假设存在合并交易图，但现实中因隐私限制无法获取完整全局图。
- 02利用端点银行已记录的交易在本地近似远程账户状态，实现无需额外交换的多层GNN计算。
- 03在AMLworld HI-Small上，可观察基线效果最佳，交易计数提供稳健修正，精确远程状态仅在特定条件下有效。
- 04隐私-效用研究表明，保护共享状态所需的噪声会消除其检测价值，而交易计数在强隐私保护下仍有效。
解读
尚无解读。
原始英文摘要
arXiv:2610.35996v1 Announce Type: cross Abstract: Most graph-based Anti-Money Laundering (AML) methods assume access to a pooled transaction graph containing all accounts and payments, which in reality does not exist. Federated learning offers the necessary privacy guarantees but it remains unclear how money laundering patterns spanning separate graphs can effectively be detected. We exploit transactions already recorded by both endpoint banks to approximate remote account states locally, enabling multi-layer Graph Neural Network (GNN) computation without additional account-specific exchange. Starting from this baseline, we test whether the remaining context is worth sharing, using a disclosure ladder that adds two transaction counts per remote account or the counterparty's own GNN states. On AMLworld HI-Small, across six GNN backbones and up to 32 silos, the observable baseline yields the largest gain and keeps it as fragmentation shrinks the visible slice; counts add a robust correction, while exact remote states help only in specific regimes. In controlled privacy--utility studies, the noise needed to protect shared states erases their detection value before it buys meaningful privacy, whereas counts stay useful even under strong privacy protection. These findings support a practical rule for banks: use what they already record, and formally protect the little that must move.