Artificial intelligence may be the key to catching cryptocurrency miners stealing computing power to mine Bitcoin and other blockchain currencies. Courtesy / LANL
Computer scientists at the Los Alamos National Laboratory have developed a new artificial intelligence (AI) system that may be able to identify malicious code that hijacks supercomputers to mine cryptocurrencies such as Bitcoin and Monero.
“Based on recent computer breaches in Europe and elsewhere, this kind of watchdog will soon be crucial in preventing cryptocurrency miners from hacking into high-performance computing facilities and stealing valuable computing resources,” Gopinath Chennupati said. , researcher in Los Alamos. National laboratory and co-author of a new article in the journal IEEE Access. “Our deep learning artificial intelligence model is designed to detect the misuse of supercomputers specifically for cryptocurrency mining purposes.”
Cryptocurrencies, such as Bitcoin, are forms of digital currency. Instead of minting it like coins or paper bills, cryptocurrency miners digitally research currency by performing arithmetic intensive calculations.
Legitimate cryptocurrency miners often assemble huge computer arrays dedicated to mining digital money. Less tasty miners discovered they could get rich by hijacking supercomputers, provided they could hide their efforts. The new AI system is designed to catch them red-handed by comparing programs based on graphics, which are like fingerprints to software.
All programs can be represented by graphics consisting of nodes linked by lines, loops or breaks. Just as human criminals can be caught by comparing whorls and arcs of fingertips to records in a fingerprint database, the new AI system compares the outlines in the flow control graph. a program has a graphics catalog for programs that are allowed to run. a given computer.
Instead of finding a match with a known criminal program, however, the system checks to see if a graphic is among those that identify programs that are supposed to be running on the system.
The researchers tested their system by comparing a known, benign code to an abusive Bitcoin mining code. They found that their system identified the illicit mining operation much faster and more reliably than conventional analyzes without AI.
Since the approach relies on chart comparisons, it cannot be fooled by common techniques illicit cryptocurrency miners use to conceal their codes, such as the inclusion of obfuscating variables and comments intended for make the codes look like legitimate programming.
While this graph-based approach may not offer a completely foolproof solution for all scenarios, it dramatically expands the set of effective approaches that cyber detectives can use in their ongoing efforts to stifle cybercriminals.
Based on recent computer break-ins, these surveillance software will soon be essential in preventing cryptocurrency miners from hacking into high-performance computing facilities and stealing valuable computing resources.
The research appeared on July 27, 2020 in the journal IEEE Access.
Publication: Code characterization with graphical convolutions and capsule arrays, Poornima Haridas, Gopinath Chennupati, Nandakishore Santhi, Phillip Romero, Stephan Eidenbenz, IEEE Access, DOI: 10.1109 / ACCESS.2020.3011909
About Los Alamos National Laboratory
Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science in the name of national security, is managed by Triad, a public service-oriented national security science organization owned equally by its three founding members: Battelle Memorial Institute (Battelle), Texas A&M University System (TAMUS) and the University of California (UC) regents for the National Nuclear Security Administration of the Department of Energy.
Los Alamos strengthens national security by ensuring the safety and reliability of the US nuclear stockpile, developing technologies to reduce threats from weapons of mass destruction, and solving energy, environmental and infrastructure issues. , health and global security issues.