Road-side Based Cybersecurity in Connected and Automated Vehicle Systems

Road-side Based Cybersecurity in Connected and Automated Vehicle Systems

Neda Masoud Headshot - link directs to their research page
Neda Masoud
Headshot of CCAT Director, Henry Liu - link directs to their research page
Henry Liu
University of Michigan Transportation Research Institute Logo - link directs to U-M research page
University of Michigan Logo - link directs to U-M research page

Principal Investigator(s):

Neda Masoud, Assistant Professor of Civil and Environmental Engineering – University of Michigan
Henry Liu, Director – Center for Connected and Automated Transportation (CCAT)
Professor of Civil and Environmental Engineering – University of Michigan
Research Professor – University of Michigan Transportation Research Institute

Project Abstract:
The objective of this research project is to further the knowledge on cybersecurity in connected and automated vehicles (CAVs). Specifically, we aim to develop a holistic framework that integrates physics-based data-driven modeling and dynamic decision making under uncertainty and partial information to improve cybersecurity in CAVs.
CAVs are anticipated to enhance our current transportation system in terms of safety and mobility, and curb the environmental implications of the transportation sector. Despite these benefits, major concerns remain as to whether an interconnected network of CAVs and infrastructure is vulnerable to malicious hackers or unintentional faults. In this proposed work, we aim to address open questions on cybersecurity of a network of connected CAVs. Our goal is to develop an integrated real-time, robust, and scalable context-aware framework to ensure safe navigation of CAVs and other road users. We will validate the framework using existing data from ongoing pilot studies as well as new simulated data which will be produced as part of this proposed work.
The proposed framework contributes to the literature of anomaly detection/identification, data fusion, non-linear control, physics-based learning, and decision making under uncertainty in novel and important ways. It will build on the state-of-the-art filters, control algorithms, and machine learning methods to address scientific challenges with respect to incorporating `context’ to improve learning and decision making under adversarial conditions. This context includes a vehicle’s motion in relationship with its surrounding traffic, which is complicated by the stochastic time delay in receiving basic safety messages from the connected vehicles/infrastructure or in collecting and contextualizing data by the vehicle’s on-board sensors.

Institution(s): University of Michigan Transportation Research Institute
University of Michigan – Ann Arbor

Award Year: 2021

Research Thrust(s): Control & Operations, Enabling Technology, Modeling & Implementation

Project Form(s):
Project Information Form