China Unveils AI-Powered Crypto Money Laundering Detection System with 90% Accuracy

China's National Police University has developed an AI algorithm to detect cryptocurrency money laundering with 90% accuracy. The system combines artificial intelligence with large language models to analyze transaction flows across blockchain networks.

The detection framework works by integrating AI-driven pattern recognition with LLM capabilities to identify anomalies indicative of layering, structuring, and other laundering techniques that criminals use to obscure the origin of illicit funds.

China's Supreme People's Procuratorate reported 3,259 people prosecuted on suspicion of money laundering involving virtual assets in 2025 alone. This highlights the growing scale of crypto-related financial crime in the country, despite strict government bans on cryptocurrency trading.

The algorithm's use of LLMs is particularly notable, as these models can interpret unstructured data to provide context that pure statistical analysis lacks. However, experts caution that the accuracy rate does not imply zero false positives and manual review and legal processes are still required to validate algorithmic flags.