FedGraph-VASP: Privacy-Preserving Federated Graph Learning with Post-Quantum Security for Cross-Institutional Anti-Money Laundering

TL;DR

FedGraph-VASP introduces a privacy-preserving federated graph learning framework secured with post-quantum cryptography, effectively detecting cross-institutional money laundering while safeguarding user data.

Contribution

It proposes a novel Boundary Embedding Exchange protocol secured with post-quantum cryptography for federated AML graph learning, outperforming existing methods in certain settings.

Findings

Achieves higher F1-score than FedSage+ on Bitcoin dataset.

Demonstrates robustness in high-connectivity regimes.

Shows topology-dependent trade-offs in graph embedding methods.

Abstract

Virtual Asset Service Providers (VASPs) face a fundamental tension between regulatory compliance and user privacy when detecting cross-institutional money laundering. Current approaches require either sharing sensitive transaction data or operating in isolation, leaving critical cross-chain laundering patterns undetected. We present FedGraph-VASP, a privacy-preserving federated graph learning framework that enables collaborative anti-money laundering (AML) without exposing raw user data. Our key contribution is a Boundary Embedding Exchange protocol that shares only compressed, non-invertible graph neural network representations of boundary accounts. These exchanges are secured using post-quantum cryptography, specifically the NIST-standardized Kyber-512 key encapsulation mechanism combined with AES-256-GCM authenticated encryption. Experiments on the Elliptic Bitcoin dataset with realistic Louvain partitioning show that FedGraph-VASP achieves an F1-score of 0.508, outperforming the state-of-the-art generative baseline FedSage+ (F1 = 0.453) by 12.1 percent on binary fraud detection. We further show robustness under low-connectivity settings where generative imputation degrades performance, while approaching centralized performance (F1 = 0.620) in high-connectivity regimes. We additionally evaluate generalization on an Ethereum fraud detection dataset, where FedGraph-VASP (F1 = 0.635) is less effective under sparse cross-silo connectivity, while FedSage+ excels (F1 = 0.855), outperforming even local training (F1 = 0.785). These results highlight a topology-dependent trade-off: embedding exchange benefits connected transaction graphs, whereas generative imputation can dominate in highly modular sparse graphs. A privacy audit shows embeddings are only partially invertible (R^2 = 0.32), limiting exact feature recovery.