After training an artificial intelligence (AI) model on a record 200 million transactions, blockchain analytics company Elliptic claimed to have found possible money laundering tendencies on the Bitcoin network.
This work is a follow-up to a 2019 program that utilized a dataset with only 200,000 transactions. 122,000 tagged "subgraphs," or collections of related nodes and transaction chains with ties to illegal activities, were used in the considerably larger "Elliptic2" dataset.
Larger datasets are needed to train machine-learning algorithms, and blockchain-based cryptocurrencies like bitcoin provide an abundance of clear transaction data. This is because AI grows more perceptive with larger datasets. According to a report co-authored by Elliptic and researchers from the MIT-IBM Watson AI Lab, Elliptic used the transactions to understand the set of "shapes" that money laundering in cryptocurrency exhibits and to accurately detect fresh criminal conduct.
In an email, co-founder of Elliptic Tom Robinson stated, "The money laundering techniques identified by the model have been identified because they are prevalent in bitcoin." "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 stated in the article.
Using "nested services," or companies that transfer money between accounts at bigger cryptocurrency exchanges—sometimes without the exchange's knowledge or consent—was another often used tactic. One of their clients may deposit money into a cryptocurrency address provided by a nested service, which would subsequently transfer the funds to the customer's exchange deposit address.
May 2024, Cryptoniteuae