Reinforcing CBDC Integrity: A Novel Anti Money Laundering Solution by Integrating Blockchain, Machine Learning, and Taint Analysis

Abstract

As the central bank digital currency (CBDC) is rapidly becoming operational, there are both opportunities for financial inclusion and efficiency, as well as problems of security threats and anti-money laundering (AML), particularly due to concerns about user anonymity. In order to address the risks associated with anonymous transactions, this research proposes a multi-layered security framework for CBDC that makes use of smart contracts built on the Ethereum platform, taint analysis, and machine learning (ML) models. The solution makes use of programmable smart contracts to automate policy enforcement and transaction validation within the CBDC ecosystem. Taint analysis techniques are incorporated to track the movement of illicit funds and identify questionable transaction patterns across the blockchain network. This is further enhanced by ML models that are optimized to learn from transaction data in order to reliably identify anomalous or illicit actions before they occur. We have generated two synthetic datasets that include two case scenarios and trained six ML models to evaluate them comparatively. Of them, random forest had the highest level of accuracy, 91.11%, in the cross-border case, whereas the support vector machine had a accuracy of 93.12% in the case of real estate transactions. In addition, we conducted a performance comparison of five environments; traditional banking, CBDC with baseline blockchain, CBDC with blockchain, CBDC with ML, and CBDC with blockchain, taint analysis and ML. We used different metrics to test the performance of our proposed scheme and found that our AML tracking algorithm took an average of 0.55 s inference time, which is faster than the underlying reference method. According to our results, the proposed combined framework ensures high-level protection that improved risk detection in digital currencies, with a significantly reduced risk of money laundering and related hazards when using CBDC systems.