A Secure Framework for Anti-Money-Laundering using Machine Learning and Secret Sharing

Nowadays, the scale of Money Laundering is difficult to estimate in the UK and elsewhere. Proceeds of crimes might be transferred using the available business infrastructure offered by banks, and this is a considerable problem. This paper outlines a novel scheme that allows banks to share information leading to Money Laundering (ML) detection all the while preserving confidentiality and integrity. The main contribution is the overall architecture that aims to improve ML detection by getting other banks to collaborate. In order to get other banks to co-operate, a primary directive of preserving privacy is enforced throughout the framework. The proposed scheme has two particular aspects, one of which is the application of encrypted data used in machine learning for ML detection. Another feature is using secret sharing as a collaborative element in this context. These aspects are found in the three phases of the framework: Signalling to the Auditor, ML Detection and finally Suspicious Activity Report (SAR) Feedback.

I. Introduction

Money laundering activity is associated with various types of crime, and efficient detection of this activity strongly contributes to the prevention and prosecution of those crimes. The true scale of this activity is difficult to estimate accurately: one estimate [1] puts the proceeds at £4.5B annually for drug supply and £5.9B for fraud. There are several categories of money laundering (ML), including the use of property, gambling, and businesses to obfuscate the true source of funds. This paper concentrates on the use of proxy or ‘mule’ accounts for the swift transfer and ‘cash out’ of illegally obtained funds. The precise manner in which these funds are obtained is not the subject of this paper, but typical examples include deceiving the bank customer into transferring funds, theft by re-ordering and then intercepting bank authentication devices, or re-registering the phone number or postal address associated with the bank account. These funds are then typically transferred again, possibly multiple times and into smaller fragments, so that the parties involved in this organised crime can securely access them.