Emerging Cyber-Pyhsical Power Electronics Attacks in Autonomous Electric Vehicles

Modern automotive cyber-physical systems utilize numerous smart technologies including sensors, wireless communication, electrified and autonomous operation. An average autonomous vehicle (AV), driving an hour per day, is expected to use massive amount of data every day, some of which will need to be communicated to outside of the AV. Meanwhile, electric vehicles (EVs) have been transforming modern transportation and energy systems, introducing fuel savings and environmental benefits which make them an attractive option for autonomous driving as well. Accordingly, to realize truly autonomous electric vehicles (AEVs), it is crucial that 1) the vehicles interact with the physical world seamlessly through sensors such as cameras, radars, and light detection and ranging sensors, and 2) the vehicles have continuous/seamless broadband connectivity with each other and the supporting infrastructure. Nonetheless, this cyberspace provides numerous opportunities for malicious actors threatening the security of the AEVs and their applications, potentially resulting in accidents, injuries, property/infrastructure damages, even taking human lives. In this paper, we analyze emerging power electronics security challenges and propose a novel preliminary countermeasure approach for the secure and dependable operation of the system. The approach considers developing a lightweight, machine learning-based intrusion detection mechanism to be deployed at the power electronics/microcontorller level such that it can deal with malicious data/control commands initiated by attacks at any level, including software, hardware, or firmware-based attacks.

[1]  Qiang Ni,et al.  Driving with Sharks: Rethinking Connected Vehicles with Vehicle Cybersecurity , 2017, IEEE Vehicular Technology Magazine.

[2]  Qiyan Wang,et al.  VeCure: A practical security framework to protect the CAN bus of vehicles , 2014, 2014 International Conference on the Internet of Things (IOT).

[3]  Jalel Ben-Othman,et al.  Survey on VANET security challenges and possible cryptographic solutions , 2014, Veh. Commun..

[4]  Jianying Zhou,et al.  A Secure, Intelligent Electric Vehicle Ecosystem for Safe Integration With the Smart Grid , 2015, IEEE Transactions on Intelligent Transportation Systems.

[5]  Matti Valovirta,et al.  Experimental Security Analysis of a Modern Automobile , 2011 .

[6]  Stefano Longo,et al.  Modern electric, hybrid electric, and fuel cell vehicles, third edition , 2018 .

[7]  Todd Litman,et al.  Autonomous Vehicle Implementation Predictions: Implications for Transport Planning , 2015 .

[8]  Florian Kerschbaum,et al.  Privacy and Integrity Considerations in Hyperconnected Autonomous Vehicles , 2018, Proceedings of the IEEE.

[9]  Chan Yeob Yeun,et al.  Recent Advances in VANET Security: A Survey , 2015, 2015 IEEE 82nd Vehicular Technology Conference (VTC2015-Fall).

[10]  Araz Taeihagh,et al.  Autonomous Vehicles for Smart and Sustainable Cities: An In-Depth Exploration of Privacy and Cybersecurity Implications , 2018, ArXiv.

[11]  Panagiotis Papadimitratos,et al.  Secure vehicular communication systems: design and architecture , 2008, IEEE Communications Magazine.

[12]  Huirong Fu,et al.  Security Threats and Countermeasures for Intra-vehicle Networks , 2009, 2009 Fifth International Conference on Information Assurance and Security.

[13]  Alejandro Quintero,et al.  VANET security surveys , 2014, Comput. Commun..

[14]  Xi Zheng,et al.  Investigating Security Vulnerabilities in Modern Vehicle Systems , 2016, ATIS.

[15]  Jonathan Miller,et al.  Cyber Threats Facing Autonomous and Connected Vehicles: Future Challenges , 2017, IEEE Transactions on Intelligent Transportation Systems.

[16]  Kara M. Kockelman,et al.  The Travel and Environmental Implications of Shared Autonomous Vehicles, Using Agent-Based Model Scenarios , 2014 .