Các nhà nghiên cứu Trung Quốc phát triển thuật toán AI để theo dõi rửa tiền bitcoin với độ chính xác khoảng 90%

The Huoxing Finance report states that on August 2, researchers from the People’s Public Security University of China developed an AI framework capable of detecting illegal cryptocurrency transactions with nearly 90% overall accuracy. The study was published in the Chinese peer-reviewed journal *Journal of Intelligence*. Dr. Sun Jingchao (specializing in criminal investigation and cybersecurity), the corresponding author, noted that this research “provides a precise, scalable, and interpretable solution for detecting illegal cryptocurrency transactions” and offers “an innovative technological pathway” for regulatory authorities to combat illegal cryptocurrency transactions and economic crimes. The AI framework leverages memory modules and large language models to specifically identify the anonymity and cross-border characteristics of cryptocurrencies, enabling the tracking of illicit activities such as money laundering. This research comes at a time when China is intensifying its crackdown on cryptocurrency-related financial crimes. In March this year, the Supreme People’s Procuratorate disclosed that Chinese prosecutors had brought charges against 3,259 individuals in 2025 for money laundering crimes involving virtual currencies and underground banks. As cryptocurrency trading volumes surge rapidly, the anonymity and cross-border nature of these transactions have created channels for illicit fund flows. This self-developed AI detection tool by law enforcement marks a shift in regulatory technology from passive tracking to proactive intelligent identification.