An Innovative Attack Modelling and Attack Detection Approach for a Waiting Time-based Adaptive Traffic Signal Controller

However, the evolution of mainstream transportation systems towards a connected cyber infrastructure, such as connected traffic signal controllers, is increasing system vulnerability to potential cyber attack, allowing malicious actors (individuals, criminals, or terrorist organizations) to exploit security vulnerabilities of such transportation infrastructure (1)-(3). In the U.S., the number of cyberattacks on smart mobility systems has jumped significantly in recent years (4). As vehicles are moving towards connected and automated driving, and cities are focusing on creating a transportation cyber infrastructure that will transform legacy transportation infrastructure to connected, adaptable, and automated systems, the security problems will only increase and further compromise public safety (5). Many studies show that a cyber attack on connected vehicle-based (CV-based) traffic signal control algorithms can break down a traffic network by creating severe congestion (6-10). An adaptive traffic signal controller (ATSC) combined with a connected vehicle (CV) concept uses real-time vehicle trajectory data to regulate green time; this combination also has the ability to reduce intersection waiting time significantly and improve travel time in a signalized corridor (11). A CV-based ATSC can be manipulated in two ways: (i) gain access through vulnerabilities and exploit the ATSC; and (ii) produce abnormal behavior through the manipulation of inputs of vehicle-related data (9).