New York: The researchers, including one among Indian-origin, tested their system by comparing a known, benign code to an abusive, Bitcoin mining code.
According to a study published in the journal IEEE Access, the system identified the illicit mining operation much quicker and more reliably than conventional, non-AI analyses.
Also Read: Insight into Twitter hacks using Bitcoin Scam by Col. Inderjeet Singh, DG, CSAI
Gopinath Chennupati, a researcher at Los Alamos National Laboratory in the US says, "Our deep-learning artificial intelligence model is designed to detect the abusive use of supercomputers specifically for the purpose of cryptocurrency mining."
He further added, "Based on recent computer break-ins in Europe and elsewhere, this sort of software watchdog will soon be crucial to stopping cryptocurrency miners from hacking into high-performance computing facilities and stealing precious computing resources."
Instead of minting it like coins or paper bills, cryptocurrency miners digitally dig for the currency by performing computationally intense calculations.
Legitimate cryptocurrency miners often assemble enormous computer arrays dedicated to exhumation the digital cash. Less savoury miners have found they can strike it rich by hijacking supercomputers, provided they can keep their efforts hidden.
Much as human criminals are often caught by comparing the whorls and arcs on their fingertips to records in a fingerprint database, the latest AI system compares the contours in a programme's flow-control graph to a catalogue of graphs for programmes that are allowed to run on a given computer.
Instead of finding a match to a known criminal programme, however, the system checks to work out whether a graph is among people who identify programmes that are supposed to be running on the system.
Because the approach relies on graph comparisons, it can’t be fooled by common techniques that illicit cryptocurrency miners use to disguise their codes, like including obfuscating variables and comments intended to make the codes look like legitimate programming, says the study.
Also Read: Facebook Classic' design set to disappear next month and much more
(Inputs from IANS)
