Man-in-the-middle attacks against unmanned military vehicles have been identified and averted with 99% efficacy by a new artificial intelligence algorithm, reports BleepingComputer.
Developed by professors at the University of South Australia and Charles Sturt University, the algorithm also yielded a false positive rate of under 2% in a replica of the U.S. Army's GVR-BOT. Node-based techniques and a flow-statistic-based metadata reading system have been integrated into the AI algorithm to facilitate elevated accuracy in determining cyberattacks, as well as the immediate shutdown of attempted intrusions, even after limited model training, according to researchers. More complex but similar robotic applications, including unmanned aircraft, could also benefit from the new AI algorithm, according to researchers.
"We are also interested in investigating the efficacy of our intrusion detection system on different robotic platforms, such as unmanned aerial vehicles, whose dynamics are reasonably faster and more complex compared to a ground robot," researchers added.
Open-source artificial intelligence compute framework Ray has been found to be impacted by a critical vulnerability, tracked as CVE-2023-48023, which could be exploited to facilitate unauthorized node access, according to SecurityWeek.
Get daily email updates
SC Media's daily must-read of the most current and pressing daily news