Use and validation of supervised machine learning approach for detection of GNSS signal spoofing

Silvio Semanjski, Alain Muls, Ivana Semanjski, Wim De Wilde

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

Abstract

Spoofing of the GNSS signals presents continuous threat to the users of safety of life applications due to unaware use of false signals in generating position and timing solution. Among numerous anti-spoofing techniques applied at different stages of the signal processing, we present approach of monitoring the cross-correlation of multiple GNSS observables and measurements as an input for supervised machine learning based approach to detect potentially spoofed GNSS signals. Both synthetic, generated in laboratory, and real-world spoofing datasets were used for verification and validation of the supervised machine learning algorithms for detection of the GNSS spoofing.

Original languageEnglish
Title of host publication2019 International Conference on Localization and GNSS, ICL-GNSS 2019 - Proceedings
EditorsJari Nurmi, Elena-Simona Lohan, Alexander Rugamer, Albert Heuberger, Wolfgang Koch
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728124452
DOIs
Publication statusPublished - Jun 2019
Event9th International Conference on Localization and GNSS, ICL-GNSS 2019 - Nuremberg, Germany
Duration: 4 Jun 20196 Jun 2019

Publication series

Name2019 International Conference on Localization and GNSS, ICL-GNSS 2019 - Proceedings

Conference

Conference9th International Conference on Localization and GNSS, ICL-GNSS 2019
Country/TerritoryGermany
CityNuremberg
Period4/06/196/06/19

Keywords

  • GNSS
  • GPS
  • Global Navigation Satellite System
  • PNT
  • Position-Navigation-Timing
  • Principal component analysis
  • SOL
  • SVM
  • Safety-of-Life
  • Spoofing
  • Support Vector Machines

Fingerprint

Dive into the research topics of 'Use and validation of supervised machine learning approach for detection of GNSS signal spoofing'. Together they form a unique fingerprint.

Cite this