China police AI detects Bitcoin laundering at 90% accuracy
Synopsis
China's national police university has built an AI model that flags illicit Bitcoin transactions at nearly 90% accuracy — a state-engineered forensics tool arriving as prosecutors indicted 3,259 people for crypto money laundering in 2025 alone.
Key Takeaways
Researchers at the People's Public Security University of China , affiliated with the Ministry of Public Security , developed an AI framework to detect illicit cryptocurrency transactions.
The system achieves nearly 90 per cent overall accuracy , according to a study published in May 2026 in the Chinese Journal of Intelligence .
Corresponding author Dr Sun Jingchao described the framework as 'precise, generalisable and interpretable.' The Supreme People's Procuratorate reported in March 2026 that prosecutors indicted 3,259 people in 2025 for money laundering via virtual currencies and underground banks.
The model is designed to be extensible beyond Bitcoin, positioning it as a broad-spectrum blockchain forensics tool for regulatory authorities.
Researchers at China's People's Public Security University of China, affiliated with the Ministry of Public Security, have developed an AI framework capable of identifying illicit cryptocurrency transactions with nearly 90 per cent overall accuracy, according to a study published in May 2026. The findings mark a significant advance in state-led tools to combat blockchain-based financial crime.
What the research found
The study, published in the peer-reviewed Chinese Journal of Intelligence, describes the framework as a 'precise, generalisable and interpretable solution for detecting illicit cryptocurrency transactions,' according to corresponding author Dr Sun Jingchao, a researcher specialising in criminal investigation and cybersecurity. The system is designed to flag suspicious on-chain activity despite the pseudonymous and cross-border nature of cryptocurrency networks.
Dr Sun also noted that the framework 'provides an innovative technological pathway for regulatory authorities to combat illicit cryptocurrency transactions and economic crimes.'
Why it matters
The scale of cryptocurrency-linked crime in China underscores the urgency of the research. In March 2026, the Supreme People's Procuratorate reported that prosecutors indicted 3,259 people in 2025 for money laundering involving virtual currencies and underground banks. Cryptocurrency transactions have grown rapidly globally, creating channels that bad actors exploit across jurisdictions.
An AI-driven detection model that operates with near-90 per cent accuracy could substantially reduce the investigative burden on law enforcement, particularly as transaction volumes continue to rise.
The competitive backdrop
China is not alone in deploying machine-learning tools for blockchain forensics. Private firms such as Elliptic have long offered commercial transaction-monitoring products to financial institutions and exchanges worldwide. What distinguishes the People's Public Security University framework is its institutional origin — built explicitly for state law enforcement — and its emphasis on interpretability, a quality that makes AI outputs actionable in legal proceedings.
The research also reflects a broader pattern in which China's security apparatus is integrating large language model and graph-analysis techniques into financial crime investigation.
What's next
The study's authors indicate the framework is designed to be generalisable, suggesting potential deployment across multiple cryptocurrency networks beyond Bitcoin. As China continues to tighten oversight of virtual asset flows, the technology could be adopted by prosecutors and financial regulators as a frontline screening tool. The trajectory of indictments — 3,259 in a single year — points to sustained enforcement pressure that tools like this are built to support.
Point of View
Not a procurement afterthought. The 3,259 indictments in 2025 reveal the scale of the problem that prompted this investment: underground banking networks have migrated to crypto rails at a pace that outstripped manual investigation. What mainstream coverage tends to miss is the interpretability emphasis: a model that can explain its outputs is one that can survive cross-examination in court, making it operationally superior to black-box commercial alternatives. The longer arc here is a global race — between state actors like China and private blockchain-analytics firms — to define the evidentiary standards for crypto crime prosecution.
NationPress
2 Aug 2026
Frequently Asked Questions
What did China's police AI research find about Bitcoin money laundering?
Researchers at the People's Public Security University of China developed an AI framework that detects illicit cryptocurrency transactions with nearly 90 per cent overall accuracy , according to a study published in May 2026 . The system is designed to be precise, generalisable, and interpretable for use by regulatory authorities.
Who conducted the cryptocurrency AI study in China?
The study was conducted by researchers from the People's Public Security University of China , which is affiliated with the Ministry of Public Security . Corresponding author Dr Sun Jingchao , a specialist in criminal investigation and cybersecurity, led the publication in the peer-reviewed Chinese Journal of Intelligence .
How many people were indicted in China for crypto money laundering?
The Supreme People's Procuratorate reported in March 2026 that prosecutors indicted 3,259 people in 2025 for money laundering involving virtual currencies and underground banks. This figure reflects the scale of enforcement pressure driving investment in AI-based detection tools.
Why is AI being used to detect cryptocurrency crime?
Cryptocurrency networks are pseudonymous and cross-border, making traditional investigative methods slow and resource-intensive. AI frameworks can analyse transaction graphs at scale, flagging suspicious patterns that would take human analysts far longer to identify, particularly as transaction volumes grow globally.
How does China's police AI compare to commercial blockchain analytics firms?
Private firms such as Elliptic offer commercial transaction-monitoring products to financial institutions worldwide, but China's framework is built explicitly for state law enforcement and emphasises interpretability — meaning its outputs can be used as evidence in legal proceedings. This gives it a practical advantage in prosecution contexts over black-box commercial tools.
