Crypto forensics firm Elliptic using advances in AI to detect bitcoin money laundering

Blockchain forensics firm Elliptic said it has made advances in using artificial intelligence to detect bitcoin money laundering.

The firm said in a statement that it is using the advancements to enhance Elliptic's detection tools and has detailed the work in a new research paper "co-authored with researchers from the MIT-IBM Watson AI Lab."

"A deep learning model is used to successfully identify proceeds of crime deposited at a crypto exchange, new money laundering transaction patterns and previously-unknown illicit wallets," the firm said in its statement.

Elliptic said it tested the enhanced tools on a dataset that contains over 200 million transactions.

"Rather than identifying transactions made by illicit actors, a machine learning model is trained to identify 'subgraphs,' chains of transactions that represent bitcoin being laundered," said Elliptic. "By identifying these subgraphs rather than illicit wallets, this approach allows us to focus on the 'multi-hop' laundering process more generally rather than the on-chain behavior of specific illicit actors."

When compared to "typically siloed" traditional financial transactions, blockchains facilitate the use of machine learning to better examine transactions, according to Elliptic.

Elliptic has a history of identifying crypto transactions made by nefarious actors like terrorist groups.