A team of US researchers has developed a new machine learning-based framework to enhance the security of computer networks inside vehicles without reducing performance.
In collaboration with experts from Virginia Tech, the University of Queensland and the Gwangju Institute of Science and Technology, researchers at the US Army Research Laboratory have devised a technology called Desolator to help optimize a well-known cybersecurity strategy.
Desolator, which stands for Deep Reinforcement Learning-Based Resource Allocation and Moving Target Defense Deployment Framework, helps identify optimal IP shuffling frequency and bandwidth allocation to provide effective, long-term moving target defense to in-vehicle networks .
The idea is that a moving target is difficult to hit, said Dr Terence Moore, a US military mathematician.
He explained in a statement, if everything is stable, the opponent can take his time looking at everything and choosing his target. But if you quickly shuffle the IP address, the information assigned to the IP is quickly lost, and the adversary has to look for it again.
New cybersecurity tech protects computer networks in vehicles #CybersecurityTech #Desolator #TechNews #Industry #CyberSecurity #Ip #CybersecurityProtection #CyberSecurityNews #Technology https://t.co/S8csmAuzt5
— ETTelecom (@ETTelecom) August 1, 2021
The research team used deep reinforcement learning to gradually shape the behavior of the algorithm based on various reward tasks, such as exposure time and number of packets dropped, to ensure that the desolator achieved both safety and efficiency. taken into account equally.
“Existing legacy in-vehicle networks are very efficient, but they weren’t really built with safety in mind,” Moore said. Nowadays, there’s a lot of research going on that only looks at enhancing performance or enhancing safety. Seeing both performance and security is a bit rare in itself, especially for in-vehicle networks.
In addition, Desolator is not limited to identifying IP shuffling frequency and bandwidth allocation.
Since this approach exists as a machine learning-based framework, other researchers can modify the technique to pursue different goals within the problem space.
According to Dr. Frederica Frey-Nelson, Army computer scientist and head of the program, this level of priority assets on the network is an integral part of any type of network security.
This ability to reimagine technology is very valuable not only for expanding research, but also for matching other cyber capabilities for optimal cybersecurity protections, Nelson said.