A deep-learning-based framework for supporting analysis and detection of attacks on CAN buses

Modern vehicles contain a plethora of electronic units aimed to send and receive data by exploiting the serial communication provided by the CAN bus. CAN packets are broadcasted to all components and it is in charge of the single component to decide if it is the receiver of the packets. Furthermore, this protocol does not provide source identification of authentication: for these reason it clear that the CAN bus can be easily exposed to attacks. In this paper we propose a method to detect CAN bus targeting attacks. We take into account deep learning algorithms and we evaluate the proposed method by exploiting CAN messages obtained from a real vehicle injecting four different attacks (i.e. dos, fuzzy, gear and rpm), with interesting results in CAN bus attacks detection.