Know your master: Driver profiling-based anti-theft method

Byung Il Kwak, Ji Young Woo, Huy Kang Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Although many anti-theft technologies are implemented, auto-theft is still increasing. Also, security vulnerabilities of cars can be used for auto-theft by neutralizing anti-theft system. This keyless auto-theft attack will be increased as cars adopt computerized electronic devices more. To detect auto-theft efficiently, we propose the driver verification method that analyzes driving patterns using measurements from the sensor in the vehicle. In our model, we add mechanical features of automotive parts that are excluded in previous works, but can be differentiated by drivers' driving behaviors. We design the model that uses significant features through feature selection to reduce the time cost of feature processing and improve the detection performance. Further, we enrich the feature set by deriving statistical features such as mean, median, and standard deviation. This minimizes the effect of fluctuation of feature values per driver and finally generates the reliable model. We also analyze the effect of the size of sliding window on performance to detect the time point when the detection becomes reliable and to inform owners the theft event as soon as possible. We apply our model with real driving and show the contribution of our work to the literature of driver identification.

Original languageEnglish
Title of host publication2016 14th Annual Conference on Privacy, Security and Trust, PST 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages211-218
Number of pages8
ISBN (Electronic)9781509043798
DOIs
Publication statusPublished - 2016
Event14th Annual Conference on Privacy, Security and Trust, PST 2016 - Auckland, New Zealand
Duration: 2016 Dec 122016 Dec 14

Other

Other14th Annual Conference on Privacy, Security and Trust, PST 2016
CountryNew Zealand
CityAuckland
Period16/12/1216/12/14

Fingerprint

larceny
driver
Railroad cars
Feature extraction
traffic behavior
Sensors
fluctuation
Processing
performance
vulnerability
Costs
electronics
event
costs
Values

Keywords

  • Anti-theft
  • Driver identification
  • Driver verification
  • Machine learning

ASJC Scopus subject areas

  • Safety Research
  • Computer Networks and Communications
  • Hardware and Architecture
  • Safety, Risk, Reliability and Quality

Cite this

Kwak, B. I., Woo, J. Y., & Kim, H. K. (2016). Know your master: Driver profiling-based anti-theft method. In 2016 14th Annual Conference on Privacy, Security and Trust, PST 2016 (pp. 211-218). [7906929] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PST.2016.7906929

Know your master : Driver profiling-based anti-theft method. / Kwak, Byung Il; Woo, Ji Young; Kim, Huy Kang.

2016 14th Annual Conference on Privacy, Security and Trust, PST 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 211-218 7906929.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kwak, BI, Woo, JY & Kim, HK 2016, Know your master: Driver profiling-based anti-theft method. in 2016 14th Annual Conference on Privacy, Security and Trust, PST 2016., 7906929, Institute of Electrical and Electronics Engineers Inc., pp. 211-218, 14th Annual Conference on Privacy, Security and Trust, PST 2016, Auckland, New Zealand, 16/12/12. https://doi.org/10.1109/PST.2016.7906929
Kwak BI, Woo JY, Kim HK. Know your master: Driver profiling-based anti-theft method. In 2016 14th Annual Conference on Privacy, Security and Trust, PST 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 211-218. 7906929 https://doi.org/10.1109/PST.2016.7906929
Kwak, Byung Il ; Woo, Ji Young ; Kim, Huy Kang. / Know your master : Driver profiling-based anti-theft method. 2016 14th Annual Conference on Privacy, Security and Trust, PST 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 211-218
@inproceedings{e2fbdbbc400b420c8e7319d71631d348,
title = "Know your master: Driver profiling-based anti-theft method",
abstract = "Although many anti-theft technologies are implemented, auto-theft is still increasing. Also, security vulnerabilities of cars can be used for auto-theft by neutralizing anti-theft system. This keyless auto-theft attack will be increased as cars adopt computerized electronic devices more. To detect auto-theft efficiently, we propose the driver verification method that analyzes driving patterns using measurements from the sensor in the vehicle. In our model, we add mechanical features of automotive parts that are excluded in previous works, but can be differentiated by drivers' driving behaviors. We design the model that uses significant features through feature selection to reduce the time cost of feature processing and improve the detection performance. Further, we enrich the feature set by deriving statistical features such as mean, median, and standard deviation. This minimizes the effect of fluctuation of feature values per driver and finally generates the reliable model. We also analyze the effect of the size of sliding window on performance to detect the time point when the detection becomes reliable and to inform owners the theft event as soon as possible. We apply our model with real driving and show the contribution of our work to the literature of driver identification.",
keywords = "Anti-theft, Driver identification, Driver verification, Machine learning",
author = "Kwak, {Byung Il} and Woo, {Ji Young} and Kim, {Huy Kang}",
year = "2016",
doi = "10.1109/PST.2016.7906929",
language = "English",
pages = "211--218",
booktitle = "2016 14th Annual Conference on Privacy, Security and Trust, PST 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Know your master

T2 - Driver profiling-based anti-theft method

AU - Kwak, Byung Il

AU - Woo, Ji Young

AU - Kim, Huy Kang

PY - 2016

Y1 - 2016

N2 - Although many anti-theft technologies are implemented, auto-theft is still increasing. Also, security vulnerabilities of cars can be used for auto-theft by neutralizing anti-theft system. This keyless auto-theft attack will be increased as cars adopt computerized electronic devices more. To detect auto-theft efficiently, we propose the driver verification method that analyzes driving patterns using measurements from the sensor in the vehicle. In our model, we add mechanical features of automotive parts that are excluded in previous works, but can be differentiated by drivers' driving behaviors. We design the model that uses significant features through feature selection to reduce the time cost of feature processing and improve the detection performance. Further, we enrich the feature set by deriving statistical features such as mean, median, and standard deviation. This minimizes the effect of fluctuation of feature values per driver and finally generates the reliable model. We also analyze the effect of the size of sliding window on performance to detect the time point when the detection becomes reliable and to inform owners the theft event as soon as possible. We apply our model with real driving and show the contribution of our work to the literature of driver identification.

AB - Although many anti-theft technologies are implemented, auto-theft is still increasing. Also, security vulnerabilities of cars can be used for auto-theft by neutralizing anti-theft system. This keyless auto-theft attack will be increased as cars adopt computerized electronic devices more. To detect auto-theft efficiently, we propose the driver verification method that analyzes driving patterns using measurements from the sensor in the vehicle. In our model, we add mechanical features of automotive parts that are excluded in previous works, but can be differentiated by drivers' driving behaviors. We design the model that uses significant features through feature selection to reduce the time cost of feature processing and improve the detection performance. Further, we enrich the feature set by deriving statistical features such as mean, median, and standard deviation. This minimizes the effect of fluctuation of feature values per driver and finally generates the reliable model. We also analyze the effect of the size of sliding window on performance to detect the time point when the detection becomes reliable and to inform owners the theft event as soon as possible. We apply our model with real driving and show the contribution of our work to the literature of driver identification.

KW - Anti-theft

KW - Driver identification

KW - Driver verification

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=85019202573&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019202573&partnerID=8YFLogxK

U2 - 10.1109/PST.2016.7906929

DO - 10.1109/PST.2016.7906929

M3 - Conference contribution

AN - SCOPUS:85019202573

SP - 211

EP - 218

BT - 2016 14th Annual Conference on Privacy, Security and Trust, PST 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -