A Zero-Trust Reinforcement Learning Policy for Mitigating Cyberattacks on Emergency Vehicle Preemption Systems

There are more than $\mathbf{3 2 0, 0 0 0}$ traffic signals in the United States. A significant number of these signals are equipped with emergency vehicle preemption (EVP) systems, where each emergency vehicle (EV) interrupts pre-designed signal operation plans, causing a disruption in signal coordination. Recently, the difficulty of configuring EVP operations has been exacerbated by the potential for cybersecurity attacks that can spoof EVP calls or prevent actual calls from reaching the traffic controllers. It is, therefore, critically important to develop robust and efficient EVP systems that can detect cybersecurity attacks and operate the EVP system safely and optimally. This paper presents a novel application of Zero-Trust Architecture (ZTA) and methods that can lead to optimal EVP control. We use a digital twin of a transportation network to simulate the EVP operation and identify system vulnerabilities using the AnyLogic agent-based simulation platform. We simulate cybersecurity attacks for both normal traffic and connected automated vehicles (CAVs) scenarios and emulate the impact of activating an anomalydetection system to identify and remove false positive calls. In addition, we present a reinforcement learning (RL) algorithm to identify true negative cases and filter out spoofed EVs when applicable.