Blockchain
Blockchain researchers use artificial intelligence to spot Bitcoin money laundering
Researchers at Elliptic, IBM Watson and MIT have used artificial intelligence to detect money laundering on the Bitcoin blockchain.
In 2019, blockchain analytics firm Elliptic published research with the MIT-IBM Watson AI Lab showing how a machine learning model could be trained to identify Bitcoin transactions made by illicit actors, such as ransomware groups or darknet marketplaces .
Now the partners have published new ones research apply new techniques to a much larger dataset, containing nearly 200 million transactions. Instead of identifying transactions made by illicit actors, a machine learning model was trained to identify “subgraphs,” chains of transactions that represent bitcoin laundering.
Identifying these subgraphs rather than illicit wallets allowed researchers to focus on the “multi-hop” money laundering process more generally rather than the on-chain behavior of specific illicit actors.
Working with a cryptocurrency exchange, the researchers tested their technique: of the 52 money laundering subgraphs predicted and resulting in deposits on the exchange, 14 were received from users who had already been reported as being linked to money laundering. money.
On average, fewer than one in 10,000 accounts are flagged this way, “suggesting that the model works very well,” the team says. The researchers are now making their underlying data public.
Elliptic says: “This new work demonstrates that artificial intelligence methods can be applied to blockchain data to identify illicit wallets and money laundering patterns, which were previously hidden from view.
“This is made possible by the inherent transparency of blockchains and demonstrates that cryptoassets, far from being a haven for criminals, are much more susceptible to AI-based financial crime detection than traditional financial assets.”