Cybersecurity of Connected and Automated Vehicles via Traffic Anomaly Detection

Cybersecurity of Connected and Automated Vehicles via Traffic Anomaly Detection

Headshot of Raphael Stern. The link directs to their profile page.
Raphael Stern
University of Minnesota Logo. The link directs to the funded research led by this institution.

Principal Investigator(s):

Raphael Stern, Assistant Professor of Civil, Environmental, and Geo-Engineering – University of Minnesota

Project Abstract:
Connected and automated vehicles (CAVs) provide new opportunities for malicious actors to compromise vehicle security and compromise traffic flow. While obvious hacks that cause crashes may be easy to identify and isolate, other vehicle compromises may be more difficult to identify, especially if the hack impacts vehicle driving behavior or causes a vehicle to transmit faulty data via vehicle-to-vehicle (V2V) or vehicle-to-infrastructure (V2I) connectivity.
In this work, we propose to previous work funded by a University of Minnesota Center for Transportation Studies seed grant which conducted trajectory anomaly detection in compromised AVs (without connectivity) to consider potential data anomalies in a connected vehicle network and identify compromised vehicles on their driving behavior and the data they are sharing across the communication network (e.g., 5G connected vehicles). Specifically, we propose to use car following models to simulate traffic flow both of typical mixed autonomy traffic as well as traffic where some of the automated vehicles have been compromised and are sending compromised communications to other vehicles. The communication layer will also be modeled independently, with vehicles sharing basic safety messages (BSMs) across the network. Potential cyberattacks will be implemented in simulation, where compromised messages are communicated across the network, and the resulting traffic and communication data as well as traffic and communication data from uncompromised traffic flow will be compared to understand the potential impact of such attacks. Furthermore, the generated synthetic data will be used to develop anomaly detection techniques that leverage advancements in neural networks and autoencoders to identify atypical traffic and communication data.

Institution(s): University of Minnesota

Award Year: 2023

Research Focus: Cybersecurity

Project Form(s):