GNSS Location Verification in Connected and Autonomous Vehicles Using in-Vehicle Multimodal Sensor Data Fusion

Abstract

Connected and Autonomous Vehicles (CAVs) rely on Global Navigation Satellite Systems (GNSS), e.g., the Global Positioning System (GPS), for the provision of accurate location information for various functionalities including Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communication and self-navigation. However, GNSSbased location awareness is prone to spoofing attacks, where the attacker generates counterfeit satellite signals. This in turn poses a serious threat to the CAV, e.g., car, drone, etc., as well as the surrounding entities. Thus, this threat needs to be detected reliably and mitigated timely to prevent undesired consequences (e.g., damages, casualties, etc.). To this end, this work proposes a location verification solution that leverages in-vehicle sensor readings (e.g., accelerometer, etc.) and Signals of Opportunity (SoO), as an alternative source of location information. In particular, the multimodal sensor data with SoO location measurements are fused by means of a Kalman filter and the estimated fusion-based location is used to verify the location output of the GPS receiver. In case the GPS location deviates considerably from the fusion-based location, then a location spoofing attack is ascertained. Preliminary experimental results with real GPS and sensor data collected with a drone demonstrate the effectiveness of the proposed approach.

Machine learning and blockchain technologies for cybersecurity in connected vehicles

“…Spurious signals can be easily detected as the signal looks different from typical satellite signals. Adding location verification, cryptography, cooperative GPS receiver through information exchange with neighboring vehicles, and using message authentication can defend vehicle's GPS from spoofing and jamming attacks (Heng et al, 2015; Milaat & Liu, 2018; Souli et al, 2020). A summary of cyberattacks and countermeasures concerning CAV sensors is presented in Table 2.…”

“…These attacks can be conducted in isolation or in support of other categories of attacks. A malicious node can either physically join the Ethernet network utilizing a free switch port (Sommer et al, 2019) or can remotely access the network by user-associated security negligence. • Traffic confidentiality attacks: This category of attack affects authentication and privacy.…”

“…Unauthorized access acquired by attackers allows them to tap on network traffic. The knowledge about network topology and structure can be gained either by transmitting messages and analyzing their replies or by attaching listening devices to the host cable/switch for traffic analysis (Sommer et al, 2019). Moreover, a malicious node can take advantage of MAC flooding attacks and eavesdrop on all frames.…”