Intrusion Detection in Autonomous Vehicular Networks: A Trust Assessment and Q-learning Approach

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

The ever-growing development of autonomous driving vehicles (ADVs) attracts a lot of attention of the intelligent industry. The security issues of the autonomous vehicular networks become essential since the automated components onboard are easily attacked which may leads ADVs malfunction. However, few of the intrusion detection systems (IDSs) used for mitigating above issues consider the intrusion detection in autonomous vehicular networks (AVNs). Therefore, in this paper, we propose a novel intrusion detection scheme for AVNs. Firstly, we establish the trust assessment model for ADVs including direct assessment and indirect assessment. Then, we present the intrusion detection model by confidence assessment to intrusion reports. Next, a Q-learning based incentive model is given to intelligently stimulate ADVs to participate the intrusion reporting. Finally, the simulation results show the efficiency of our proposal compared with conventional schemes in detection rate.

Original languageEnglish
Title of host publicationINFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages79-83
Number of pages5
ISBN (Electronic)9781728118789
DOIs
StatePublished - Apr 2019
Externally publishedYes
Event2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019 - Paris, France
Duration: 29 Apr 20192 May 2019

Publication series

NameINFOCOM 2019 - IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019

Conference

Conference2019 INFOCOM IEEE Conference on Computer Communications Workshops, INFOCOM WKSHPS 2019
Country/TerritoryFrance
CityParis
Period29/04/192/05/19

Keywords

  • Autonomous vehicular networks
  • Intrusion detection
  • Q-learning
  • trust assessment

Fingerprint

Dive into the research topics of 'Intrusion Detection in Autonomous Vehicular Networks: A Trust Assessment and Q-learning Approach'. Together they form a unique fingerprint.

Cite this