After utilizing a record 200 million transactions to train an artificial intelligence (AI) model, the blockchain analytics company Elliptic claimed to have found possible money laundering tendencies on the Bitcoin blockchain.This work is an expansion of a program that was implemented in 2019 with a dataset consisting of just 200,000 transactions.Twelve2,000 tagged “subgraphs,” or collections of related nodes and transaction chains with ties to illegal activities, were used in the much larger “Elliptic2” dataset.
The bigger the information that is available to train the machine-learning algorithms, the more perceptive AI gets, and cryptocurrencies like bitcoin provide an abundance of clear transaction data on the blockchain.Elliptic said in a paper co-authored with researchers from the MIT-IBM Watson AI Lab that it used the transactions to accurately categorize fresh criminal behavior and learn the collection of “shapes” that money laundering displays in cryptocurrencies.
“The money laundering techniques identified by the model have been identified because they are prevalent in bitcoin,” Elliptic co-founder Tom Robinson said in an email. “Crypto laundering practices will evolve over time as they cease being effective, but an advantage of an AI/deep learning approach is that new money laundering patterns are identified automatically as they emerge.”
It was discovered that a large number of the suspicious subgraphs included “peeling chains,” in which a user transfers some money to a destination address and sends the rest to a different address that they control.A peeling chain is formed by this happening repeatedly.
“In traditional finance this is known as ‘smurfing,’ where large amounts of cash are structured into multiple small transactions, to keep them under regulatory reporting limits and avoid detection,” Elliptic said in the paper.
Another method that was frequently used was the employment of “nested services,” which are companies that transfer money between accounts at bigger cryptocurrency exchanges, sometimes without the exchange’s knowledge or consent.When a consumer deposits money into a cryptocurrency address, a nested service may accept it, process it, and send the money to the customer’s exchange deposit address.
“Nested services are known to frequently have less stringent customer due diligence checks than the cryptocurrency exchanges they utilize, or sometimes have no such anti-money laundering checks at all, resulting in their misuse for cryptocurrency laundering – potentially causing them to feature in subgraphs deemed by the model as suspicious,” said Elliptic.