Los Alamos National Laboratory, partly-owned by the U.S. Department of Energy's National Nuclear Security Administration, has developed an artificial intelligence (AI)-based system to detect illicit cryptocurrency miners.
The system is specifically designed for malicious actors that target supercomputers to mine cryptocurrencies like bitcoin (BTC) and monero (XMR), the laboratory announced on Thursday. Recent reports have indicated that academic supercomputers are targeted by would-be attackers to install crypto mining hardware.
The laboratory's AI system relies on graph comparisons, which are like fingerprints for software. "Much as human criminals can be caught by comparing the whorls and arcs on their fingertips to records in a fingerprint database, the new AI system compares the contours in a program's flow-control graph to a catalog of graphs for programs that are allowed to run on a given computer," said the laboratory.
The laboratory acknowledged that the system might not be entirely foolproof for all scenarios, but cyberdetectives can use it along with other tools to catch cybercriminals.