Blockchain analytics firm Elliptic said its researchers have made progress in leveraging artificial intelligence (AI) to detect money laundering in Bitcoin.
A recent paper detailing this research was co-authored with researchers at the MIT-IBM Watson AI Lab. Elliptic revealed successful identification of illicit proceeds deposited on a cryptocurrency exchange, new patterns of money laundering transactions and previously unidentified illegal wallets through the use of a deep learning model.
The company said the results are already being used to improve its products.
Revealing hidden money laundering schemes
The underlying data has been made public. With over 200 million transactions, this dataset will enable the community to create new AI methods to identify illegal cryptocurrency activities, Elliptic said in a statement. statement this week.
Instead of identifying transactions made by criminals, a machine learning model is trained to recognize “subgraphs” – which are essentially chains of transactions indicative of Bitcoin laundering. This method focuses on identifying these subgraphs rather than illicit wallets, allowing Elliptic to focus on the broader “multi-hop” laundering process rather than the specific on-chain actions of individual criminals.
Elliptic said it leveraged an undisclosed cryptocurrency exchange to test whether the technique could detect money laundering attempts through it. Of the 52 planned “money laundering” subcharts ending in deposits on this exchange, 14 have been confirmed by the exchange to be linked to reported users. On average, less than one account in 10,000 is reported, which demonstrates the good performance of the model.
“We've barely scratched the surface of what's possible in this area, but this work has already brought benefits to Elliptic users. Increased collaboration and data sharing will be key to advancing these techniques and combatting financial crime linked to cryptoassets.
The role of AI in the blockchain sector
AI tools are gradually showing an exceptional ability to analyze large data sets to detect patterns beyond human perception, such as identifying illegal money movements within the Bitcoin economy.
So it's no surprise that venture capital investments in Web3 and AI startups have exceeded $637 million in 2023.
In fact, AI agents are expected to dominate the blockchain industry in 2024 to establish a more secure and efficient ecosystem, as stated in a report by Nansen.
Binance Free $600 (CryptoPotato Exclusive): Use this link to create a new account and receive an exclusive $600 welcome offer on Binance (all the details).
2024 LIMITED OFFER for CryptoPotato readers at Bybit: Use this link to sign up and open a $500 BTC-USDT position on Bybit Exchange for free!