Researchers at the US Army Research Laboratory developed a technique called ‘DESOLATOR’ in collaboration with experts from Virginia Tech, the University of Queensland, and the Gwangju Institute of Science and Technology to help optimise a well-known cybersecurity strategy known as the moving target defence.
A group of researchers from the United States has created a new machine learning-based framework to improve the security of computer networks inside automobiles without sacrificing performance.
Researchers at the US Army Research Laboratory developed a technique called ‘DESOLATOR’ in collaboration with experts from Virginia Tech, the University of Queensland, and the Gwangju Institute of Science and Technology to help optimise a well-known cybersecurity strategy known as the moving target defence.
DESOLATOR, which stands for deep reinforcement learning-based resource allocation and moving target defence deployment framework, aids the in-vehicle network in identify the best IP shuffling frequency and bandwidth allocation for long-term moving target defence.
Commenting on the development, Dr Terrence Moore, a US Army Mathematician, said “The idea is that it’s hard to hit a moving target,”
He explained in a statement, “If everything is static, the adversary can take their time looking at everything and choosing their targets. But if you shuffle the IP addresses fast enough, then the information assigned to the IP quickly becomes lost, and the adversary has to look for it again,”
To guarantee that DESOLATOR took both security and efficiency into account, the research team used deep reinforcement learning to gradually alter the behaviour of the algorithm based on several reward functions, such as exposure time and the number of dropped packets.
Moore said “Existing legacy in-vehicle networks are very efficient, but they weren’t really designed with security in mind,”
“Nowadays, there’s a lot of research out there that looks solely at either enhancing performance or enhancing security. Looking at both performance and security is in itself a little rare, especially for in-vehicle networks.”
DESOLATOR is also capable of identifying the optimal IP shuffling frequency and bandwidth allocation.
Because this approach is based on machine learning based framework, it can be modified by other researchers to pursue different goals within the problem space.
This level of fortification of prioritised assets on a network, according to Army computer scientist and programme lead Dr Frederica Free-Nelson, is an integrated component for any form of network protection.
Nelson said “This ability to retool the technology is very valuable not only for extending the research but also marrying the capability to other cyber capabilities for optimal cybersecurity protection,”