For many years, car keys have been the sole mean of authentication in vehicles. Whether the access control process is physical or wireless, entrusting the ownership of a vehicle to a single token is prone to stealing attempts. For this reason, many researchers started developing behavior-based authentication systems. By collecting data in a moving vehicle, Deep Learning (DL) models can recognize patterns in the data and identify drivers based on their driving behavior. This can be used as an anti-theft system, as a thief would exhibit a different driving style compared to the vehicle owner's. However, the assumption that an attacker cannot replicate the legitimate driver behavior falls under certain conditions. In this paper, we propose GAN-CAN, the first attack capable of fooling state-of-the-art behavior-based driver authentication systems in a vehicle. Based on the adversary's knowledge, we propose different GAN-CAN implementations. Our attack leverages the lack of security in the Controller Area Network (CAN) to inject suitably designed time-series data to mimic the legitimate driver. Our design of the malicious time series results from the combination of different Generative Adversarial Networks (GANs) and our study on the safety importance of the injected values during the attack. We tested GAN-CAN in an improved version of the most efficient driver behavior-based authentication model in the literature. We prove that our attack can fool it with an attack success rate of up to 0.99. We show how an attacker, without prior knowledge of the authentication system, can steal a car by deploying GAN-CAN in an off-the-shelf system in under 22 minutes.

翻译：暂无翻译