Bitcoin
Vast New Dataset Could Boost AI’s Pursuit of Crypto Money Laundering
As a test of the resulting AI tool, the researchers cross-checked their results with a cryptocurrency exchange – which the article does not name – identifying 52 suspicious chains of transactions that ultimately flowed to that exchange. It turned out that the exchange had already flagged 14 of the accounts that received these funds for suspected illicit activity, including eight that were flagged as associated with money laundering or fraud, based in part on information known to its customer that it had requested . account owners. Despite not having access to “know your customer” data or any information about the origin of funds, the researchers’ AI model matched the conclusions of the exchange’s own researchers.
Correctly identifying 14 out of 52 customer accounts as suspicious may not seem like a high success rate, but researchers point out that only 0.1% of the exchange’s accounts are flagged as potential money laundering overall. Their automated tool, they argue, has essentially reduced the search for suspicious accounts to more than one in four. “Going from ‘one in a thousand things we see will be illicit’ to 14 in 52 is an absurd change,” says Mark Weber, one of the paper’s co-authors and a member of the MIT Media Lab. “And now the investigators are actually going to dig into the rest to see, wait, did we miss something?”
Elliptic says it already uses the AI model privately in its own work. As further evidence that the AI model is producing useful results, the researchers write that analyzing the source of funds for some suspicious transaction chains identified by the model helped them discover Bitcoin addresses controlled by a Russian dark web marketplace, a Cryptocurrency “mixer” designed to obfuscate the trail of bitcoins on the blockchain and a Panama-based Ponzi scheme. (Elliptic declined to identify any of these alleged criminals or services by name, telling WIRED that it does not identify the targets of ongoing investigations.)
Perhaps more important than the practical use of the researchers’ own AI model, however, is the potential of Elliptic’s training data, which the researchers have Published on the Google-owned machine learning and data science community site Kaggle. “Elliptic could have kept this to itself,” says MIT’s Weber. “Instead, there was an open-source spirit here of contributing something to the community that will allow everyone, even your competitors, to be better at combating money laundering.” Elliptic notes that the data released is anonymized and does not contain any identifiers of Bitcoin address owners or even the addresses themselves, just the structural data of the “subgraphs” of transactions it has marked with its suspected money laundering classifications.
This massive data set will undoubtedly inspire and enable much more AI-focused research into bitcoin money laundering, says Stefan Savage, a professor of computer science at the University of California, San Diego, who served as an advisor to the lead author of a study. . seminal paper on bitcoin tracking published in 2013. He argues, however, that the current tool does not appear to revolutionize anti-money laundering efforts in crypto in its current form so much as serve as a proof of concept. “I think an analyst will sometimes struggle with a tool that is right,” says Savage. “I see this as a breakthrough that says, ‘Hey, there’s something here. More people should work on this.’”