Feature selection for anomaly detection in vehicular ad hoc networks

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

1 Citation (Scopus)

Abstract

An emerging trend to improve automotive safety is the development of Vehicle-to-Vehicle (V2V) safety applications. These applications use information gathered from the vehicle's sensors and from surrounding vehicles to detect and prevent imminent crashes. Vehicles have been equipped with external communication interfaces to make these applications possible, but this also exposes them to security threats. If an attacker is able to feed safety applications with incorrect data, they might actually cause accidents rather than prevent them. In this paper, we investigate the application of white-box anomaly detection to detect such attacks. A key step in applying such an approach is the selection of the “right” behavioral features, i.e. features that allow the detection of attacks and provide an understanding of the raised alerts. By finding meaningful features and building accurate models of normal behavior, this work makes a first step towards the design of effective anomaly detection engines for V2V communication.

LanguageEnglish
Title of host publicationProceedings of the 15th International Joint Conference on e-Business and Telecommunications
EditorsAngel Serrano Sanchez de Leon, Paulo Novais, Sebastiano Battiato, Panagiotis Sarigiannidis, Mohammad S. Obaidat, Mohammad S. Obaidat, Christian Callegari, Marten van Sinderen, Pascal Lorenz
Place of PublicationSetúbal
PublisherSCITEPRESS-Science and Technology Publications, Lda.
Pages481-491
Number of pages11
ISBN (Electronic)978-989-758-319-3
DOIs
StatePublished - 1 Jan 2018
Event15th International Joint Conference on e-Business and Telecommunications, ICETE 2018 - Porto, Portugal
Duration: 26 Jul 201828 Jul 2018

Conference

Conference15th International Joint Conference on e-Business and Telecommunications, ICETE 2018
CountryPortugal
CityPorto
Period26/07/1828/07/18

Fingerprint

Vehicular ad hoc networks
Feature extraction
Information use
Communication
Accidents
Engines
Sensors

Keywords

  • Anomaly Detection
  • Basic Safety Message
  • Crash Avoidance Systems
  • Vehicular Ad Hoc Network

Cite this

Le, V. H., den Hartog, J., & Zannone, N. (2018). Feature selection for anomaly detection in vehicular ad hoc networks. In A. S. S. de Leon, P. Novais, S. Battiato, P. Sarigiannidis, M. S. Obaidat, M. S. Obaidat, C. Callegari, M. van Sinderen, ... P. Lorenz (Eds.), Proceedings of the 15th International Joint Conference on e-Business and Telecommunications (pp. 481-491). Setúbal: SCITEPRESS-Science and Technology Publications, Lda.. DOI: 10.5220/0006946804810491
Le, Van Huynh ; den Hartog, Jerry ; Zannone, Nicola. / Feature selection for anomaly detection in vehicular ad hoc networks. Proceedings of the 15th International Joint Conference on e-Business and Telecommunications. editor / Angel Serrano Sanchez de Leon ; Paulo Novais ; Sebastiano Battiato ; Panagiotis Sarigiannidis ; Mohammad S. Obaidat ; Mohammad S. Obaidat ; Christian Callegari ; Marten van Sinderen ; Pascal Lorenz. Setúbal : SCITEPRESS-Science and Technology Publications, Lda., 2018. pp. 481-491
@inproceedings{860e3632e9a64b118f3df1a3a1bbc608,
title = "Feature selection for anomaly detection in vehicular ad hoc networks",
abstract = "An emerging trend to improve automotive safety is the development of Vehicle-to-Vehicle (V2V) safety applications. These applications use information gathered from the vehicle's sensors and from surrounding vehicles to detect and prevent imminent crashes. Vehicles have been equipped with external communication interfaces to make these applications possible, but this also exposes them to security threats. If an attacker is able to feed safety applications with incorrect data, they might actually cause accidents rather than prevent them. In this paper, we investigate the application of white-box anomaly detection to detect such attacks. A key step in applying such an approach is the selection of the “right” behavioral features, i.e. features that allow the detection of attacks and provide an understanding of the raised alerts. By finding meaningful features and building accurate models of normal behavior, this work makes a first step towards the design of effective anomaly detection engines for V2V communication.",
keywords = "Anomaly Detection, Basic Safety Message, Crash Avoidance Systems, Vehicular Ad Hoc Network",
author = "Le, {Van Huynh} and {den Hartog}, Jerry and Nicola Zannone",
year = "2018",
month = "1",
day = "1",
doi = "10.5220/0006946804810491",
language = "English",
pages = "481--491",
editor = "{de Leon}, {Angel Serrano Sanchez} and Paulo Novais and Sebastiano Battiato and Panagiotis Sarigiannidis and Obaidat, {Mohammad S.} and Obaidat, {Mohammad S.} and Christian Callegari and {van Sinderen}, Marten and Pascal Lorenz",
booktitle = "Proceedings of the 15th International Joint Conference on e-Business and Telecommunications",
publisher = "SCITEPRESS-Science and Technology Publications, Lda.",

}

Le, VH, den Hartog, J & Zannone, N 2018, Feature selection for anomaly detection in vehicular ad hoc networks. in ASS de Leon, P Novais, S Battiato, P Sarigiannidis, MS Obaidat, MS Obaidat, C Callegari, M van Sinderen & P Lorenz (eds), Proceedings of the 15th International Joint Conference on e-Business and Telecommunications. SCITEPRESS-Science and Technology Publications, Lda., Setúbal, pp. 481-491, 15th International Joint Conference on e-Business and Telecommunications, ICETE 2018, Porto, Portugal, 26/07/18. DOI: 10.5220/0006946804810491

Feature selection for anomaly detection in vehicular ad hoc networks. / Le, Van Huynh; den Hartog, Jerry; Zannone, Nicola.

Proceedings of the 15th International Joint Conference on e-Business and Telecommunications. ed. / Angel Serrano Sanchez de Leon; Paulo Novais; Sebastiano Battiato; Panagiotis Sarigiannidis; Mohammad S. Obaidat; Mohammad S. Obaidat; Christian Callegari; Marten van Sinderen; Pascal Lorenz. Setúbal : SCITEPRESS-Science and Technology Publications, Lda., 2018. p. 481-491.

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

TY - GEN

T1 - Feature selection for anomaly detection in vehicular ad hoc networks

AU - Le,Van Huynh

AU - den Hartog,Jerry

AU - Zannone,Nicola

PY - 2018/1/1

Y1 - 2018/1/1

N2 - An emerging trend to improve automotive safety is the development of Vehicle-to-Vehicle (V2V) safety applications. These applications use information gathered from the vehicle's sensors and from surrounding vehicles to detect and prevent imminent crashes. Vehicles have been equipped with external communication interfaces to make these applications possible, but this also exposes them to security threats. If an attacker is able to feed safety applications with incorrect data, they might actually cause accidents rather than prevent them. In this paper, we investigate the application of white-box anomaly detection to detect such attacks. A key step in applying such an approach is the selection of the “right” behavioral features, i.e. features that allow the detection of attacks and provide an understanding of the raised alerts. By finding meaningful features and building accurate models of normal behavior, this work makes a first step towards the design of effective anomaly detection engines for V2V communication.

AB - An emerging trend to improve automotive safety is the development of Vehicle-to-Vehicle (V2V) safety applications. These applications use information gathered from the vehicle's sensors and from surrounding vehicles to detect and prevent imminent crashes. Vehicles have been equipped with external communication interfaces to make these applications possible, but this also exposes them to security threats. If an attacker is able to feed safety applications with incorrect data, they might actually cause accidents rather than prevent them. In this paper, we investigate the application of white-box anomaly detection to detect such attacks. A key step in applying such an approach is the selection of the “right” behavioral features, i.e. features that allow the detection of attacks and provide an understanding of the raised alerts. By finding meaningful features and building accurate models of normal behavior, this work makes a first step towards the design of effective anomaly detection engines for V2V communication.

KW - Anomaly Detection

KW - Basic Safety Message

KW - Crash Avoidance Systems

KW - Vehicular Ad Hoc Network

UR - http://www.scopus.com/inward/record.url?scp=85059104419&partnerID=8YFLogxK

U2 - 10.5220/0006946804810491

DO - 10.5220/0006946804810491

M3 - Conference contribution

SP - 481

EP - 491

BT - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications

PB - SCITEPRESS-Science and Technology Publications, Lda.

CY - Setúbal

ER -

Le VH, den Hartog J, Zannone N. Feature selection for anomaly detection in vehicular ad hoc networks. In de Leon ASS, Novais P, Battiato S, Sarigiannidis P, Obaidat MS, Obaidat MS, Callegari C, van Sinderen M, Lorenz P, editors, Proceedings of the 15th International Joint Conference on e-Business and Telecommunications. Setúbal: SCITEPRESS-Science and Technology Publications, Lda.2018. p. 481-491. Available from, DOI: 10.5220/0006946804810491