Researchers from blockchain forensic firm Elliptic, IBM Watson and MIT have together made advances in using artificial intelligence (AI) to identify money laundering on the Bitcoin blockchain.
A recent report released Wednesday by Elliptic revealed that the researchers used deep learning model to successfully detect crypto crimes. Dubbed “Enhancing Blockchain Analytics Through AI,” the findings aim to help customers to assess risks in crypto assets, more accurately.
New Elliptic research released today explores how #AI can be leveraged to detect money laundering and other financial crime on the blockchain. The research applies new techniques to a dataset containing 200m+ transactions, which is now publicly available. https://t.co/k3GdjWJ08P
— Elliptic (@elliptic) May 1, 2024
The deep learning AI model detects money laundering patterns and identify crypto wallets used in crimes, it noted. Elliptic wrote that unlike traditional finance, where transaction data is typically “siloed” making it challenging, blockchain provides transparency to apply these techniques.
“Blockchains provide fertile ground for machine learning techniques, thanks to the availability of both transaction data and information on the types of entities that are transacting, collected by us and others.”
Further, Elliptic highlighted how a machine learning model is trained to detect ‘subgraphs’ chains of transactions, which are known to represent Bitcoin money laundering.
“This approach allows us to focus on the ‘multi-hop’ laundering process more generally rather than the on-chain behavior of specific illicit actors,” it added.
Put simply, the researchers used patterns of Bitcoin transactions that led from bad actors to crypto exchanges. They used these example patterns to train an AI model, which spots similar money movements of suspected money laundering behavior.
The company noted that it applied the AI advanced tools to test a dataset containing over 200 million transactions.
Crypto 2023 Was Marred by Money Laundering
Crypto’s 14th year in existence – 2023 – highlighted $22.2 billion worth of cryptocurrency laundered, according to Chainalysis’s report.
However, the figures were a significant decrease from the $31.5 billion recorded in 2022. The good news is that “the drop in money laundering activity was steeper, at 29.5%, compared to the 14.9% drop in total transaction volume.”
Notably, the crypto laundering tactics have changed with most sophisticated criminals utilizing bridges and mixers.
Governments have placed increasing emphasis in recent years on the need for increased vigilance with regard to AML rules.
For instance, this week, Binance’s ex-CEO Changpeng Zhao was sentenced to four months in federal prison for money laundering violations. He was pled guilty to money laundering in 2023, marking a major turning point for the world’s largest crypto exchange.
In yet another case last month, US authorities arrested founders of Bitcoin mixer Samourai over money laundering charges. The founders allegedly executed over $2 billion in unlawful transactions and laundering over $100 million in criminal proceeds.
The post AI Could Detect Money Laundering on Bitcoin Blockchain: Elliptic Report appeared first on Cryptonews.