Chinese police university researchers build AI system to trace Bitcoin laundering with about 90% accuracy

Researchers at the People’s Public Security University of China have developed an AI framework that can detect illicit cryptocurrency transactions with an overall accuracy of close to 90%, according to BlockBeats.

The study was published in the Chinese peer-reviewed journal Intelligence Magazine. Its corresponding author, Dr. Sun Jingchao, whose research focuses on criminal investigation and cybersecurity, said the work provides “an accurate, scalable and explainable solution” for detecting illegal cryptocurrency transactions. He said it also offers regulators “an innovative technical path” for fighting illicit crypto activity and economic crime.

The framework uses a memory module and a large language model to identify the anonymous and cross-border features of cryptocurrency activity. It is designed to track money laundering and other illicit transactions.

The study was released as China continues to intensify its crackdown on financial crimes tied to cryptocurrency. In March this year, China’s Supreme People’s Procuratorate disclosed that prosecutors had already charged 3,259 people in 2025 in money laundering cases involving virtual currencies and underground banks.

As cryptocurrency trading volume grows quickly, its anonymous and cross-border features have created channels for illicit fund flows. The report said the AI detection tool, developed independently by police researchers, shows that regulatory technology is moving from passive tracking toward active and intelligent identification.