HybridFL: A Federated Learning Approach for Financial Crime Detection

2026-02-22

AI Summary

This work addresses the challenge of financial crime detection under hybrid data partitioning, where data is simultaneously split across users (horizontally) and features (vertically). To tackle this, we propose HybridFL, a novel framework that seamlessly integrates horizontal federated learning with secure vertical feature fusion, enabling end-to-end privacy-preserving collaborative modeling between transacting parties and multiple banks without sharing raw data. HybridFL is designed for real-world heterogeneous data distributions and balances privacy and model performance through horizontal model aggregation and encrypted vertical feature interaction. Experiments on the AMLSim and SWIFT datasets demonstrate that HybridFL significantly outperforms baseline models trained solely on local transaction data and achieves performance close to that of centralized training.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Federated learning (FL) is a privacy-preserving machine learning paradigm that enables multiple parties to collaboratively train models on privately owned data without sharing raw information. While standard FL typically addresses either horizontal or vertical data partitions, many real-world scenarios exhibit a complex hybrid distribution. This paper proposes Hybrid Federated Learning (HybridFL) to address data split both horizontally across disjoint users and vertically across complementary feature sets. We evaluate HybridFL in a financial crime detection context, where a transaction party holds transaction-level attributes and multiple banks maintain private account-level features. By integrating horizontal aggregation and vertical feature fusion, the proposed architecture enables joint learning while strictly preserving data locality. Experiments on AMLSim and SWIFT datasets demonstrate that HybridFL significantly outperforms the transaction-only local model and achieves performance comparable to a centralized benchmark.

Problem

• federated learning
• financial crime detection
• hybrid data partition
• data locality
• privacy-preserving machine learning

Innovation

• Hybrid Federated Learning
• horizontal and vertical partitioning
• financial crime detection
• privacy-preserving machine learning
• feature fusion