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

2026-01-25

AI Summary

This study addresses the dilemma faced by virtual asset service providers in cross-institutional anti-money laundering efforts, where existing approaches either risk exposing sensitive data or fail to detect cross-chain laundering patterns due to isolated analysis. To reconcile privacy preservation with collaborative detection, the authors propose a privacy-preserving federated graph learning framework featuring a novel boundary account embedding exchange protocol. This protocol shares only compressed, irreversible embeddings generated by graph neural networks, while ensuring communication security through post-quantum encryption (Kyber-512) and AES-256-GCM. Evaluated on the Elliptic Bitcoin dataset, the method achieves an F1 score of 0.508, representing a 12.1% improvement over FedSage+. Privacy audits confirm limited reconstructability of the shared embeddings (R² = 0.32), demonstrating an effective balance between detection performance and data privacy.

Technology Category

• Machine Learning: Privacy
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web

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.

Problem

• anti-money laundering
• privacy-preserving
• federated graph learning
• cross-institutional collaboration
• user privacy

Innovation

• Federated Graph Learning
• Post-Quantum Cryptography
• Boundary Embedding Exchange
• Anti-Money Laundering
• Privacy-Preserving AI