Vehicular Communications · 2019 · 313 citations · 209 references
ComputingAutomotive EngineeringCybersecurityAutonomous VehiclesSecurity ArchitectureVehicle DynamicsAutomotive SensorsCyber-physical SecurityVehicle ControlVehicle Control SystemsVehicle CybersecurityVehicle-to-everything CommunicationAutonomous Vehicle SecurityCybersecurity VulnerabilityEnvironmental SensorsSecurity In Vehicular NetworksState-of-the-art ReviewVehicle SecurityVehicle-to-everything Communication SecurityVehicle-to-vehicle Communication Security
Modern vehicles rely on V2X and in‑vehicle connectivity, exposing sensing, communication, and control layers to eavesdropping, jamming, spoofing, and other cyber‑attacks that can propagate and compromise autonomous functions. The paper proposes a three‑layer framework (sensing, communication, control) to better understand automotive security threats and reviews state‑of‑the‑art attacks and countermeasures. The authors construct the framework by modeling each layer’s vulnerabilities and conduct a comprehensive review of communication‑layer attacks and corresponding defenses.
As modern vehicles are capable to connect to an external infrastructure and Vehicle-to-Everything (V2X) communication technologies mature, the necessity to secure communications becomes apparent. There is a very real risk that today's vehicles are subjected to cyber-attacks that target vehicular communications. This paper proposes a three-layer framework (sensing, communication and control) through which automotive security threats can be better understood. The sensing layer is made up of vehicle dynamics and environmental sensors, which are vulnerable to eavesdropping, jamming, and spoofing attacks. The communication layer is comprised of both in-vehicle and V2X communications and is susceptible to eavesdropping, spoofing, man-in-the-middle, and sybil attacks. At the top of the hierarchy is the control layer, which enables autonomous vehicular functionality, including the automation of a vehicle's speed, braking, and steering. Attacks targeting the sensing and communication layers can propagate upward and affect the functionality and can compromise the security of the control layer. This paper provides the state-of-the-art review on attacks and threats relevant to the communication layer and presents countermeasures.
209
Proceedings of the 11th USENIX Security Symposium
Dan Boneh · 2002 · 2.5K citations
A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks
Chuanlong Yin, Yuefei Zhu, Jinlong Fei et al. · IEEE Access · 2017 · 2K citations · Full text