Chinese police AI algorithm tracks bitcoin money laundering with 90% accuracy
Researchers from China’s national police academy have developed an AI framework that can detect illicit cryptocurrency transactions with nearly 90 per cent overall accuracy, according to a recent study. Cryptocurrency transactions are growing rapidly, but their pseudonymous and cross-border nature can provide channels for money laundering and other illegal activities. In an article published in…
Chinese police researchers have developed an AI algorithm capable of detecting illicit cryptocurrency transactions with a near 90 percent accuracy rate, according to a recent study published in the peer-reviewed Chinese Journal of Intelligence. The AI framework, created by researchers from the People's Public Security University of China, utilizes a dynamic graph neural network, a memory module, and a large language model (LLM) to analyze cryptocurrency transactions.
This innovative system can identify patterns and money flows within the cryptocurrency ecosystem, which is notorious for its pseudonymous and cross-border nature, making it attractive for money laundering and other illegal activities. The study, led by Dr. Sun Jingchao, emphasizes the potential of this technology to aid regulatory authorities in combating illicit cryptocurrency transactions and economic crimes.
The researchers tested their AI model on the public Elliptic bitcoin transaction dataset, consisting of 203,769 transaction nodes, 234,355 edges and 166 features for each node. The system achieved an overall accuracy of 89.4 percent, with a precision of 89.1 percent for illicit transactions and a recall rate of 64.5 percent. This means that nearly every transaction flagged as illicit by the AI was indeed illegal in the actual dataset, while the system identified around two-thirds of the labelled illegal transactions.
Written by urgent.news from South China Morning Post's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
