Abstract
Vehicle and road side unit communications are crucial to the information network in Intelligent Transportation System (ITS). There are two fundamental problems with the current communication security solutions: (1) encryption technology alone is not sufficient to verify the authenticity of the messages transmitted from vehicles to road side units, (2) existing solutions fail to build a complete framework in the way that they are case-dependent and apply to limited scenarios. This paper first presents a cloud-vehicle-road architecture that explains the precise message contents as well as the message generation and transmission process. A binary classification model is deployed to assess uploaded traffic-related messages to improve traffic efficiency based on cross-sectional data. A novel graph temporal neural network with attention is designed for misbehavior detection of vehicles based on time-sequential data. According to simulation results, the system's overall performance can be effectively improved regarding security and availability.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
