Secure passive keyless entry and start system using machine learning

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

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

5 Citations (Scopus)

Abstract

Despite the benefits of the passive keyless entry and start (PKES) system in improving the locking and starting capabilities, it is vulnerable to relay attacks even though the communication is protected using strong cryptographic techniques. In this paper, we propose a dataintensive solution based on machine learning to mitigate relay attacks on PKES Systems. The main contribution of the paper, beyond the novelty of the solution in using machine learning, is in (1) the use of a set of security features that accurately profiles the PKES system,(2) identifying abnormalities in PKES regular behavior, and (3) proposing a countermeasure that guarantees a desired probability of detection with a fixed false alarm rate by trading off the training time and accuracy. We evaluated our method using the last three months log of a PKES system using the Decision Tree, SVM, KNN and ANN and provide the comparative analysis of the relay attack detection results. Our proposed framework leverages the accuracy of supervised learning on known classes with the adaptability of k-fold cross-validation technique for identifying malicious and suspicious activities. Our test results confirm the effectiveness of the proposed solution in distinguishing relayed messages from legitimate transactions.
Original languageEnglish
Title of host publicationSecurity, Privacy and Anonymity in Computation, Communication and Storage
Subtitle of host publication11th International Conference and Satellite Workshops, SpaCCS 2018. Proceedings
EditorsGuojun Wang, Jinjun Chen, Laurence T. Yang
Place of PublicationCham
PublisherSpringer
Pages304-313
Number of pages10
ISBN (Electronic)9783030053451
ISBN (Print)9783030053444
DOIs
Publication statusPublished - 2018
Externally publishedYes
Event11th International Conference on Security, Privacy and Anonymity in Computation, Communication, and Storage (SpaCCS 2018) - Melbourne, Australia
Duration: 11 Dec 201813 Dec 2018

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume11342
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference11th International Conference on Security, Privacy and Anonymity in Computation, Communication, and Storage (SpaCCS 2018)
CountryAustralia
CityMelbourne
Period11/12/1813/12/18

Keywords

  • Internet of Things
  • Machine learning
  • Passive keyless entry and start
  • Relay attack
  • Vehicle security

Fingerprint Dive into the research topics of 'Secure passive keyless entry and start system using machine learning'. Together they form a unique fingerprint.

Cite this