"Simulating Self-Driving Security"
Self-driving technology has the potential to save lives, but the addition of autonomous vehicles increases the number of cyberattack targets on the road, endangering not just those in the impacted vehicle but also those in adjacent vehicles and buildings. Road testing to improve security is costly and time-consuming, but Commonwealth Cyber Initiative (CCI) researchers have created a virtual alternative consisting of a digital library of real-world driving scenarios to help car manufacturers develop more secure autonomous vehicles. A team from the Virginia Tech-affiliated organization Global Center for Automotive Performance Simulation (GCAPS) is collaborating with researchers at the Virginia Tech Transportation Institute (VTTI) to evaluate the performance and security of automated technologies. Their project is backed by the "Innovation: Ideation to Commercialization" program of the CCI in Southwest Virginia, which provides funding to commercialize technology stemming from research at the intersection of data, security, and autonomy. Virtual, scenario-based testing is a safe, cost-effective option as opposed to the traditional distance-based validation of autonomous technology, which requires driving billions of miles on public highways, a process that is difficult and sometimes impossible. According to Miguel Perez, associate professor of biomedical engineering and mechanics and director of the VTTI data engineering program, the library provides ground truth based on real-world data for vehicle interactions with the road, infrastructure, vulnerable road users, and other vehicles. This article continues to discuss researchers' efforts to build and commodify a massive virtual data library of real-world road events to bolster the security of autonomous vehicles.