Federated learning enhances cross-bank anti-money laundering detection

Researchers have developed a novel approach to Anti-Money Laundering (AML) using federated learning and graph neural networks. This method allows banks to detect money laundering patterns that span across separate transaction graphs without needing to exchange sensitive account data. The study found that approximating remote account states using already recorded transactions provided the most significant gains in detection, even as data fragmentation increased. Sharing exact remote states proved less effective, as privacy protection measures often diminished their detection value. AI

IMPACT This research offers a privacy-preserving method for detecting sophisticated money laundering schemes across financial institutions.

RANK_REASON Academic paper detailing a new method for anti-money laundering using federated learning and graph neural networks. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• AMLworld HI-Small
• Anti-money laundering
• arXiv
• CatalyzeX
• DagsHub
• federated learning
• Gotit.pub
• graph neural network
• Hugging Face
• Influence Flower
• ScienceCast

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →