Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks

Tianyi Li; Raphael Stern

doi:10.1109/DI-CPS56137.2022.00012

Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks

Tianyi Li, Raphael Stern

Civil, Environmental, and Geo- Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

The possibility of using infrastructure-based sensors to identify individual vehicles, and then actuate transportation control infrastructure in response to their individual dynamics will enable to next generation of traffic infrastructure control. However, any such system to identify individual vehicles in the flow will be prone to faulty data or worse, cyberattacks where a malicious actor intentionally injects faulty data. With this context in mind, we investigate the resilience of a recently proposed deep learning based approach to identify individual vehicles in the traffic flow. We conduct numerical experiments where increasing amounts of noise is injected into time series trajectory data and conclude that while the proposed classification method is accurate at identifying individual vehicles when there is no noise, classification accuracy deteriorates quickly when noise is injected.

Original language	English (US)
Title of host publication	Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	36-39
Number of pages	4
ISBN (Electronic)	9781665470421
DOIs	https://doi.org/10.1109/DI-CPS56137.2022.00012
State	Published - 2022
Event	2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022 - Virtual, Online, Italy Duration: May 3 2022 → …

Publication series

Name	Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022

Conference

Conference	2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022
Country/Territory	Italy
City	Virtual, Online
Period	5/3/22 → …

Bibliographical note

Funding Information:
This work is supported by the University of Minnesota Center for Transportation Studies through the Transportation Scholar’s Program.

Publisher Copyright:
© 2022 IEEE.

Keywords

Adaptive cruise control
Cyber security
Vehicle identification

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Publisher link

10.1109/DI-CPS56137.2022.00012

Find It

Find It at U of M Libraries

Cite this

Li, T., & Stern, R. (2022). Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks. In Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022 (pp. 36-39). (Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/DI-CPS56137.2022.00012

Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks. / Li, Tianyi; Stern, Raphael.
Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 36-39 (Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, T & Stern, R 2022, Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks. in Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022. Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022, Institute of Electrical and Electronics Engineers Inc., pp. 36-39, 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022, Virtual, Online, Italy, 5/3/22. https://doi.org/10.1109/DI-CPS56137.2022.00012

Li T, Stern R. Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks. In Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 36-39. (Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022). doi: 10.1109/DI-CPS56137.2022.00012

Li, Tianyi ; Stern, Raphael. / Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks. Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 36-39 (Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022).

@inproceedings{0e1f125230d042f4beaf6a703098721a,

title = "Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks",

abstract = "The possibility of using infrastructure-based sensors to identify individual vehicles, and then actuate transportation control infrastructure in response to their individual dynamics will enable to next generation of traffic infrastructure control. However, any such system to identify individual vehicles in the flow will be prone to faulty data or worse, cyberattacks where a malicious actor intentionally injects faulty data. With this context in mind, we investigate the resilience of a recently proposed deep learning based approach to identify individual vehicles in the traffic flow. We conduct numerical experiments where increasing amounts of noise is injected into time series trajectory data and conclude that while the proposed classification method is accurate at identifying individual vehicles when there is no noise, classification accuracy deteriorates quickly when noise is injected.",

keywords = "Adaptive cruise control, Cyber security, Vehicle identification",

author = "Tianyi Li and Raphael Stern",

note = "Funding Information: This work is supported by the University of Minnesota Center for Transportation Studies through the Transportation Scholar{\textquoteright}s Program. Publisher Copyright: {\textcopyright} 2022 IEEE.; 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022 ; Conference date: 03-05-2022",

year = "2022",

doi = "10.1109/DI-CPS56137.2022.00012",

language = "English (US)",

series = "Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "36--39",

booktitle = "Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022",

}

TY - GEN

T1 - Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks

AU - Li, Tianyi

AU - Stern, Raphael

PY - 2022

Y1 - 2022

N2 - The possibility of using infrastructure-based sensors to identify individual vehicles, and then actuate transportation control infrastructure in response to their individual dynamics will enable to next generation of traffic infrastructure control. However, any such system to identify individual vehicles in the flow will be prone to faulty data or worse, cyberattacks where a malicious actor intentionally injects faulty data. With this context in mind, we investigate the resilience of a recently proposed deep learning based approach to identify individual vehicles in the traffic flow. We conduct numerical experiments where increasing amounts of noise is injected into time series trajectory data and conclude that while the proposed classification method is accurate at identifying individual vehicles when there is no noise, classification accuracy deteriorates quickly when noise is injected.

AB - The possibility of using infrastructure-based sensors to identify individual vehicles, and then actuate transportation control infrastructure in response to their individual dynamics will enable to next generation of traffic infrastructure control. However, any such system to identify individual vehicles in the flow will be prone to faulty data or worse, cyberattacks where a malicious actor intentionally injects faulty data. With this context in mind, we investigate the resilience of a recently proposed deep learning based approach to identify individual vehicles in the traffic flow. We conduct numerical experiments where increasing amounts of noise is injected into time series trajectory data and conclude that while the proposed classification method is accurate at identifying individual vehicles when there is no noise, classification accuracy deteriorates quickly when noise is injected.

KW - Adaptive cruise control

KW - Cyber security

KW - Vehicle identification

UR - http://www.scopus.com/inward/record.url?scp=85134306107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85134306107&partnerID=8YFLogxK

U2 - 10.1109/DI-CPS56137.2022.00012

DO - 10.1109/DI-CPS56137.2022.00012

M3 - Conference contribution

AN - SCOPUS:85134306107

T3 - Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022

SP - 36

EP - 39

BT - Proceedings - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd Workshop on Data-Driven and Intelligent Cyber-Physical Systems for Smart Cities Workshop, DI-CPS 2022

Y2 - 3 May 2022

ER -

Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Publisher link

Find It

Other files and links

Fingerprint

Cite this