Protecting our community from the hidden vulnerabilities of today's ITS

Modern vehicles generally contain 70 or more electric control modules which manage and control everything from anti-lock brake and traction to cruise control systems, door lock, and instrument cluster lights. These control modules all communicate to each other through the internal vehicle network (IVN) which is predominantly made up of a two-wire bus called the controller area network bus (CAN Bus). The main objectives of this proposal are threefold: (1) to study the impact of location poisoning in sensed vehicular data; (2) to design a reconfigurable accelerator based on an adaptive framework for secure design, implementation, and evaluation of the Internet of Vehicles (IoV); and (3) to drive the reconfigurability of (2) using the findings from (1). This project aims to make revolutionary progress to close the gap between the existing security mechanisms (e.g. multi-factor authentication), current decentralized vehicular security solutions (e.g. defense in depth), and the security needs of the IoV data. The project’s closely intertwined research activities include: (1) designing a modular framework for secure implementation of emerging autonomous and connected vehicles, covering deterrent, preventive, detective, corrective, and recovery controls; (2) developing and tuning Deep Learning architectures to classify malicious behaviors and target agents using sensed data as the input; and (3) designing the accelerator hardware to translate the security findings into actionable criteria. The Research Questions are: a) What are the security vulnerabilities and challenges presented by the poisoning the sensed data during the training process? b) Can neural networks be as successful in security of connected vehicles as they have been in computer vision and speech recognition? c) How different are the security gaps for connected vehicles from those of traditional networks? and d) Can security by design in hardware outperform the existing security patches and protocols?

Principal Investigator: 

Shahab Tayeb

PI Contact Information: 

tayeb@csufresno.edu

California State University, Fresno

Dates: 

January 2021 to December 2021

Impacts/Benefits of Implementation: 

The lack of efficient security protocols in the CAN bus standard creates a high-risk environment for all drivers and passengers and the society. By studying and performing penetration testing on the CAN bus, we aim to create solutions to fill in the gaps and improve the security of the vehicular industry. We also see opportunities to use the IVN to introduce new automation or technology to increase driver and passenger safety. With the proliferation of support for autonomous and connected vehicles in private and public sectors, many IoV of different types, sizes, and sensitivity levels exist. Autonomous and connected vehicles are increasingly gaining momentum across different disciplines but lack of standards and models for their secure design and implementation are major barriers ahead of such research and development. Advances in IoV security enabled by this research will lead to a wider adoption of connected vehicular networks in various societal applications, especially in critical areas and communities such as the Central Valley and California. Such research has the potential to be receive significant positive coverage by local and regional media. The proposed research breaks new ground in the security of vehicular networks and is the first of its kind at Fresno State and the results of this research will form the preliminary results of major funding proposals pave the path to securing extramural funding from funding bodies including the NSF, the DHS, and the DoD. The results will also be submitted for publication to top academic conferences and journals in the fields of cybersecurity and vehicular technologies. The proposed capacity building on IoV security research will have positive economic impacts in Fresno and Central Valley. A significant outcome resulting will be the adoption of the secured vehicular networks in the region and this research will foster collaborations with local government and local industry.

Project Number: 

2132