According to CryptoPotato, Elliptic, a blockchain analytics company, has reported advancements in using artificial intelligence (AI) to identify money laundering in Bitcoin. The company, in collaboration with researchers from the MIT-IBM Watson AI Lab, has published a paper detailing this research. The deep learning model used by Elliptic has successfully identified illicit proceeds deposited at a cryptocurrency exchange, new patterns of money laundering transactions, and previously unidentified illegal wallets. The findings are already being implemented to enhance the firm's products.
The data underlying this research, comprising over 200 million transactions, has been made public. This will enable the community to develop new AI methods for detecting illegal cryptocurrency activities. Instead of identifying transactions made by criminals, the machine learning model is trained to recognize 'subgraphs', which are essentially chains of transactions indicating Bitcoin laundering. This approach focuses on identifying these subgraphs rather than illicit wallets, allowing Elliptic to concentrate on the broader 'multi-hop' laundering process rather than the specific on-chain actions of individual criminals.
Elliptic tested this technique with an undisclosed cryptocurrency exchange to see if it could detect money laundering attempts. Out of 52 predicted 'money laundering' subgraphs ending with deposits to this exchange, 14 were confirmed by the exchange to be linked to flagged users. On average, less than one in 10,000 accounts are flagged, indicating the model's strong performance. The company believes that further collaboration and data-sharing will be key to advancing these techniques further and combating financial crime in crypto assets.
AI tools are gradually demonstrating exceptional capability in analyzing extensive data sets to flag patterns beyond human perception, such as identifying illegal money movements within the Bitcoin economy. As a result, VC investment in Web3 and AI startups exceeded $637 million in 2023. AI agents are projected to dominate the blockchain sector in 2024 to establish a more secure and efficient ecosystem, according to a report by Nansen.
