(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)
Researchers at US-based Los Alamos National Laboratory (LANL) have developed an artificial intelligence (AI) algorithm to detect illicit cryptocurrency miners who use research computers for mining.
“Our deep learning artificial intelligence model is designed to detect the abusive use of supercomputers specifically for the purpose of cryptocurrency mining,” said Gopinath Chennupati, a researcher at Los Alamos National Laboratory.
Cryptocurrency mining requires a lot of computing power as miners perform computationally intense calculations to mine cryptocurrencies such as Bitcoin, Ethereum, and Monero.
As a result, miners tend to assemble arrays of computer to mine cryptocurrency. Cryptocurrency miners try to use the high computational capability of supercomputers and keep the hijacking process hidden.
The new AI system is designed to identity malicious codes that hijack supercomputers to mine cryptocurrency. It compares the programs used to misuse the supercomputers, based on graphs, which are like fingerprints for software, LANL said.
Just like criminals can be caught by comparing their fingerprints with a fingerprint database, the AI system compares a program’s flow-control graph with a catalogue of graphs for programs that are allowed to run on a particular computer, it explained.
The researchers found that their system identified the unauthorised mining operation quicker than conventional, non-AI analyses, when they tested the system by comparing an authentic code with an abusive, Bitcoin mining code.
As their approach relies on graph comparisons to spot illegitimate programming, the researchers claim it cannot be fooled by commonly used masking techniques used by illicit cryptocurrency miners to disguise their codes as legitimate programs.