Researchers at China’s national police academy have built an AI framework that flags illicit bitcoin transactions with close to 90 percent accuracy, the South China Morning Post reported on Aug. 2, 2026, citing a study published in the peer reviewed Journal of Intelligence.
The framework comes from the People’s Public Security University of China, an institution under the Ministry of Public Security, and pairs a memory module with a large language model to catch laundering patterns that are pseudonymous and cross borders.
Corresponding author Dr. Sun Jingchao says the design gives regulators a repeatable way to trace illicit cryptocurrency transactions, arriving as Chinese prosecutors report thousands of virtual currency laundering indictments each year.
The Memory Module Behind the 90% Accuracy Score
According to the South China Morning Post, the May study frames its approach as a precise, generalizable and interpretable solution for detecting illicit cryptocurrency transactions. Sun credits the memory module with letting the model retain transaction context across multiple hops instead of scoring each transfer alone. That matters because laundering networks typically move funds through several wallets before cashing out.
The timing lines up with a broader enforcement push. China’s Supreme People’s Procuratorate reported in March that prosecutors indicted 3,259 people in 2025 for money laundering tied to virtual currencies and underground banks, per the same South China Morning Post report. That growth, plus crypto’s pseudonymous and cross-border reach, is why Sun’s team built a model instead of relying only on manual review.
AI Tracing Tools Are Spreading Beyond Law Enforcement
Sun’s framework is not an isolated case. On Jul. 31, 2026, Cointelegraph reported that crypto forensics firm AMLBot launched an AI Tracer letting anyone without specialist training trace bitcoin fund movements across wallets and bridges.
That tool mirrors the shift happening inside Chinese law enforcement, where AI now handles pattern-matching that once took analysts hours, a shift worth tracking alongside other developments in our crypto news section.
Whether the Framework Moves From Research Paper to Live Enforcement
The next thing to watch is whether China’s police agencies move Sun’s model past the research stage and into active casework. Neither Sun nor the university has announced a deployment timeline. Confirmation of live use would mark the clearest sign this shifts from a published study to evidence prosecutors can cite in court.
What This Means for You
If you hold or trade bitcoin, tools like this signal that blockchain surveillance is getting more precise, not less, even where crypto trading is banned outright. Pseudonymity is not the same as anonymity, since forensic AI can now trace multi-hop transfers that once looked disconnected. Anyone moving funds through exchanges with a large Chinese user base should expect more transactions to get flagged as these tools move from research papers into active use.
This article is for informational purposes only and does not constitute financial advice. Do your own research before making any investment decisions.
