Detection of Cyber-Attacks in Automotive Traffic Using Macroscopic Models and Gaussian Processes

This letter considers a class of cyber-attacks wherein an attacker has the ability to hack into a subset of vehicles driving on a highway and inject subtle changes into their driving parameters. By performing such changes, these vehicles (referred to as malicious vehicles) are able to modify the driving behavior of the overall vehicle stream. The traffic system comprising the mix of malicious and normal vehicles are modeled using a system of Partial Differential Equations (PDEs). In this letter, we develop a method that employs Gaussian Processes (GP) with the two-species PDE model, to detect the presence of such malicious vehicles in such a mixed traffic scenario. Simulation results demonstrate that the proposed GP-based detection architecture can successfully detect the percentage of malicious vehicles in the traffic, as well as their mode of attack.