"Cybersecurity Technique Protects in-Vehicle Networks"

Army researchers have developed a new machine learning-based framework to improve the security of vehicles' computer networks without weakening performance. This development supports a larger Army effort to invest in more advanced cybersecurity protection measures for aerial and land platforms. Researchers at the U.S. Army Combat Capabilities Development Command, known as DEVCOM, Army Research Laboratory, in collaboration with a team of experts from Virginia Tech, the University of Queensland, and Gwangju Institute of Science and Technology, came up with a technique called DESOLATOR, which stands for deep reinforcement learning-based resource allocation and moving target defense deployment framework. This method helps optimize a well-known cybersecurity strategy called the moving target defense. The idea behind this strategy is that it is hard for adversaries to hit a moving target. The adversary could get a better look at everything and choose their targets if everything was static. However, if IP addresses were shuffled fast enough, then the information assigned to the IP is quickly lost, thus requiring the adversary to look for it again. DESOLATOR helps computer networks inside vehicles identify the optimal IP shuffling frequency and bandwidth allocation for the delivery of effective and long-term moving target defense. Dr. Frederica Free-Nelson, Army computer scientist and program lead, said DESOLATOR facilitates lightweight protection in which fewer resources are used for maximized protection. DESOLATOR is beneficial as it utilizes fewer resources to safeguard mission systems and connected devices in vehicles while preserving the same service quality. This article continues to discuss how the new machine learning-based framework DESOLATOR bolsters the cybersecurity of in-vehicle networks.

Homeland Security News Wire reports "Cybersecurity Technique Protects in-Vehicle Networks"