"The H2020 CARAMEL Project Ends by Opening Promising New Research Avenues in the Field of Innovative Anti-hacking Solutions for the Future of Connected and Automated Vehicles"
The EU Horizon 2020 program-funded project called CARAMEL concluded, opening promising new research areas in the realm of innovative anti-hacking solutions for the future of Connected and Automated Vehicles (CAVs). The CARAMEL project partners have created a number of innovative tools and solutions based on Machine Learning (ML) and Artificial Intelligence (AI) for holistically improving the cybersecurity aspects of CAVs, contributing to the long-term vision of safer roads with zero fatalities. The solutions ranged from ML algorithms for protecting against malicious attacks on the different sensors used by a vehicle to perceive its environment, detection of attacks on vehicle message exchanges, detection of spoofing attacks on external sources of information, defense against electromobility infrastructure abuse, and anomaly detection algorithms for remotely connected vehicles. The solutions were tested experimentally on the field and in simulated environments before being integrated into embedded platforms and real autonomous vehicles. The KIOS Center of Excellence (CoE) research team created two novel solutions for detecting vehicle cyberattacks. The DriveGuard solution employs AI methods to detect and mitigate attacks on the CAV's camera system. These attacks can disrupt the original images captured by the camera sensor and the CAV's situational awareness while moving. The GPS location anti-spoofing solution is an in-vehicle detection scheme that uses multi-source data fusion from onboard sensors to detect and mitigate GPS location spoofing attacks that could impact the CAV's location awareness, causing it to collide with other vehicles or obstacles. This article continues to discuss the success of the CARAMEL project.