In-Vehicle False Information Attack Detection and Mitigation Strategies for Connected and Autonomous Vehicle
(Room Palms Ballroom - Booth 100)
16 Jul 19
5:30 PM
-
7:00 PM
A modern vehicle usually contains many electronic control units (ECUs) which communicate with each other through the Controller Area Network (CAN) bus to ensure safety and performance. Emerging Connected and Automated Vehicles (CAVs) will have more ECUs and coupling between them due to the vast array of additional sensors, advanced driving features (such as lane keeping and navigation) and vehicle-to-Everything (V2X) connectivity. As a result, CAVs will also have more vulnerabilities within the in-vehicle network. In recent years, research has proved that vehicle control can be accessed through various ways. For example, over-the-air software updates containing malware can compromise the ECUs and allow access for the attacker. False wheel speed data can cause incorrect braking. In this study, our goal is to investigate Software Defined Networking (SDN) based in-vehicle network. In particular, there are three contributions of this study. At first, we will develop an attack model and create attack datasets for false information attacks on brake-related ECUs in an SDN based in-vehicle network. Second, we develop a machine-learning based false information attack/anomaly detection model that detects, in real time, any anomalies within the in-vehicle networks. Third, we want to develop the policies for mitigating the effect of the attack using the SDN framework. SDN offers greater flexibility and resource management in defense of cyber-attacks while minimizing network congestion.