Forgery Trajectory Injection Attack Detection for Traffic Lights under Connected Vehicle Environment

With the connected vehicle (CV) can interact with the infrastructure and can be used as a moving sensor to bring more real-time and higher precision input for intersection signal control. However, such connectivity also brings network security risks.To protect the signal security of intersections, this paper designs a realistic signal attack model based on forged trajectory injection to simulate the potential attack that a smart attacker may launch, the key track points of queued vehicles were extracted, the traffic wave velocity of queued vehicles was used as the distance index to transform forged track recognition into an outlier detection problem, and a forged track detection algorithm based on hierarchical clustering was proposed. Experimental results show that under different attack targets and permeability, the highest detection rate is 95%, and the lowest is 67%. This method does not require training, learning and high computation power of edge equipment. Therefore, it has a certain potential for intersection signal timing using CV trajectory.