Securing smart vehicles from relay attacks using machine learning

Usman Ahmad, Hong Song, Awais Bilal, Mamoun Alazab, Alireza Jolfaei

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Due to the rapid developments in intelligent transportation systems, modern vehicles have turned into intelligent transportation means which are able to exchange data through various communication protocols. Today’s vehicles portray best example of a cyber-physical system because of their integration of computational components and physical systems. As the IoT and data remain intrinsically linked together, the evolving nature of the transportation network comes with a risk of virtual vehicle hijacking. In this paper, we propose a combination of machine learning techniques to mitigate the relay attacks on Passive Keyless Entry and Start (PKES) systems. The proposed algorithm uses a set of key fob features that accurately profiles the PKES system and a set of driving features to identify the driver. First relay attack detection is performed, and if a relay attack is not detected, the vehicle is unlocked and algorithm proceeds to gain the driving features and use neural networks to identify whether the current driver is whom he/she claims to be. To assess the machine learning model, we compared the decision tree, SVM, and KNN method using a three-month log of a PKES system. Our test results confirm the effectiveness of the proposed method in recognizing relayed messages. The proposed methods achieve 99.8% accuracy rate. We used a Long Short-Term Memory recurrent neural network for driver identification based on the real-world driving data, which are collected from a driver who drives the vehicles on several routes in real-world traffic conditions.

Original languageEnglish
Pages (from-to)1-18
Number of pages18
JournalJournal of Supercomputing
DOIs
Publication statusE-pub ahead of print - 30 Oct 2019

Fingerprint

Relay
Learning systems
Machine Learning
Attack
Driver
Intelligent Transportation Systems
Transportation Networks
Memory Term
Recurrent neural networks
Data Exchange
Recurrent Neural Networks
Electronic data interchange
Communication Protocol
Decision trees
Decision tree
Traffic
Neural Networks
Neural networks
Network protocols
Model

Cite this

Ahmad, Usman ; Song, Hong ; Bilal, Awais ; Alazab, Mamoun ; Jolfaei, Alireza. / Securing smart vehicles from relay attacks using machine learning. In: Journal of Supercomputing. 2019 ; pp. 1-18.
@article{775f9fa9075b4a83889766cee650f0bb,
title = "Securing smart vehicles from relay attacks using machine learning",
abstract = "Due to the rapid developments in intelligent transportation systems, modern vehicles have turned into intelligent transportation means which are able to exchange data through various communication protocols. Today’s vehicles portray best example of a cyber-physical system because of their integration of computational components and physical systems. As the IoT and data remain intrinsically linked together, the evolving nature of the transportation network comes with a risk of virtual vehicle hijacking. In this paper, we propose a combination of machine learning techniques to mitigate the relay attacks on Passive Keyless Entry and Start (PKES) systems. The proposed algorithm uses a set of key fob features that accurately profiles the PKES system and a set of driving features to identify the driver. First relay attack detection is performed, and if a relay attack is not detected, the vehicle is unlocked and algorithm proceeds to gain the driving features and use neural networks to identify whether the current driver is whom he/she claims to be. To assess the machine learning model, we compared the decision tree, SVM, and KNN method using a three-month log of a PKES system. Our test results confirm the effectiveness of the proposed method in recognizing relayed messages. The proposed methods achieve 99.8{\%} accuracy rate. We used a Long Short-Term Memory recurrent neural network for driver identification based on the real-world driving data, which are collected from a driver who drives the vehicles on several routes in real-world traffic conditions.",
keywords = "Driver identification, Machine learning, Neural networks, PKES, Relay attacks, Security",
author = "Usman Ahmad and Hong Song and Awais Bilal and Mamoun Alazab and Alireza Jolfaei",
year = "2019",
month = "10",
day = "30",
doi = "10.1007/s11227-019-03049-4",
language = "English",
pages = "1--18",
journal = "Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",

}

Securing smart vehicles from relay attacks using machine learning. / Ahmad, Usman; Song, Hong; Bilal, Awais; Alazab, Mamoun; Jolfaei, Alireza.

In: Journal of Supercomputing, 30.10.2019, p. 1-18.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Securing smart vehicles from relay attacks using machine learning

AU - Ahmad, Usman

AU - Song, Hong

AU - Bilal, Awais

AU - Alazab, Mamoun

AU - Jolfaei, Alireza

PY - 2019/10/30

Y1 - 2019/10/30

N2 - Due to the rapid developments in intelligent transportation systems, modern vehicles have turned into intelligent transportation means which are able to exchange data through various communication protocols. Today’s vehicles portray best example of a cyber-physical system because of their integration of computational components and physical systems. As the IoT and data remain intrinsically linked together, the evolving nature of the transportation network comes with a risk of virtual vehicle hijacking. In this paper, we propose a combination of machine learning techniques to mitigate the relay attacks on Passive Keyless Entry and Start (PKES) systems. The proposed algorithm uses a set of key fob features that accurately profiles the PKES system and a set of driving features to identify the driver. First relay attack detection is performed, and if a relay attack is not detected, the vehicle is unlocked and algorithm proceeds to gain the driving features and use neural networks to identify whether the current driver is whom he/she claims to be. To assess the machine learning model, we compared the decision tree, SVM, and KNN method using a three-month log of a PKES system. Our test results confirm the effectiveness of the proposed method in recognizing relayed messages. The proposed methods achieve 99.8% accuracy rate. We used a Long Short-Term Memory recurrent neural network for driver identification based on the real-world driving data, which are collected from a driver who drives the vehicles on several routes in real-world traffic conditions.

AB - Due to the rapid developments in intelligent transportation systems, modern vehicles have turned into intelligent transportation means which are able to exchange data through various communication protocols. Today’s vehicles portray best example of a cyber-physical system because of their integration of computational components and physical systems. As the IoT and data remain intrinsically linked together, the evolving nature of the transportation network comes with a risk of virtual vehicle hijacking. In this paper, we propose a combination of machine learning techniques to mitigate the relay attacks on Passive Keyless Entry and Start (PKES) systems. The proposed algorithm uses a set of key fob features that accurately profiles the PKES system and a set of driving features to identify the driver. First relay attack detection is performed, and if a relay attack is not detected, the vehicle is unlocked and algorithm proceeds to gain the driving features and use neural networks to identify whether the current driver is whom he/she claims to be. To assess the machine learning model, we compared the decision tree, SVM, and KNN method using a three-month log of a PKES system. Our test results confirm the effectiveness of the proposed method in recognizing relayed messages. The proposed methods achieve 99.8% accuracy rate. We used a Long Short-Term Memory recurrent neural network for driver identification based on the real-world driving data, which are collected from a driver who drives the vehicles on several routes in real-world traffic conditions.

KW - Driver identification

KW - Machine learning

KW - Neural networks

KW - PKES

KW - Relay attacks

KW - Security

UR - http://www.scopus.com/inward/record.url?scp=85074682059&partnerID=8YFLogxK

U2 - 10.1007/s11227-019-03049-4

DO - 10.1007/s11227-019-03049-4

M3 - Article

SP - 1

EP - 18

JO - Journal of Supercomputing

JF - Journal of Supercomputing

SN - 0920-8542

ER -