Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

GPS-IDS: An Anomaly-based GPS Spoofing Attack Detection Framework for Autonomous Vehicles

Murad Mehrab Abrar, Amal Youssef, Raian Islam, Shalaka Satam, Banafsheh Saber Latibari, Salim Hariri, Sicong Shao, Soheil Salehi, Pratik Satam

TL;DR

GPS-IDS addresses GPS spoofing threats in autonomous vehicles by marrying a physics-based AV behavior model with data-driven anomaly analysis. The framework introduces an AV-specific dynamic representation, extracts temporal features, and uses ML to distinguish normal from spoofed navigation signals, validated on a real AV-GPS-Dataset and CARLA simulations. Real data achieve up to 4% false margins with F1 scores around 94%, while simulated data reach up to 97% F1, with detection times markedly faster than EKF-based GPS/INS detectors. The work provides a public AV-GPS-Dataset and demonstrates a scalable approach that can complement sensor-level IDS to enhance AV navigation security in urban environments.

Abstract

Autonomous Vehicles (AVs) heavily rely on sensors and communication networks like Global Positioning System (GPS) to navigate autonomously. Prior research has indicated that networks like GPS are vulnerable to cyber-attacks such as spoofing and jamming, thus posing serious risks like navigation errors and system failures. These threats are expected to intensify with the widespread deployment of AVs, making it crucial to detect and mitigate such attacks. This paper proposes GPS Intrusion Detection System, or GPS-IDS, an Anomaly-based intrusion detection framework to detect GPS spoofing attacks on AVs. The framework uses a novel physics-based vehicle behavior model where a GPS navigation model is integrated into the conventional dynamic bicycle model for accurate AV behavior representation. Temporal features derived from this behavior model are analyzed using machine learning to detect normal and abnormal navigation behaviors. The performance of the GPS-IDS framework is evaluated on the AV-GPS-Dataset -- a GPS security dataset for AVs comprising real-world data collected using an AV testbed, and simulated data representing urban traffic environments. To the best of our knowledge, this dataset is the first of its kind and has been publicly released for the global research community to address such security challenges.

GPS-IDS: An Anomaly-based GPS Spoofing Attack Detection Framework for Autonomous Vehicles

TL;DR

GPS-IDS addresses GPS spoofing threats in autonomous vehicles by marrying a physics-based AV behavior model with data-driven anomaly analysis. The framework introduces an AV-specific dynamic representation, extracts temporal features, and uses ML to distinguish normal from spoofed navigation signals, validated on a real AV-GPS-Dataset and CARLA simulations. Real data achieve up to 4% false margins with F1 scores around 94%, while simulated data reach up to 97% F1, with detection times markedly faster than EKF-based GPS/INS detectors. The work provides a public AV-GPS-Dataset and demonstrates a scalable approach that can complement sensor-level IDS to enhance AV navigation security in urban environments.

Abstract

Autonomous Vehicles (AVs) heavily rely on sensors and communication networks like Global Positioning System (GPS) to navigate autonomously. Prior research has indicated that networks like GPS are vulnerable to cyber-attacks such as spoofing and jamming, thus posing serious risks like navigation errors and system failures. These threats are expected to intensify with the widespread deployment of AVs, making it crucial to detect and mitigate such attacks. This paper proposes GPS Intrusion Detection System, or GPS-IDS, an Anomaly-based intrusion detection framework to detect GPS spoofing attacks on AVs. The framework uses a novel physics-based vehicle behavior model where a GPS navigation model is integrated into the conventional dynamic bicycle model for accurate AV behavior representation. Temporal features derived from this behavior model are analyzed using machine learning to detect normal and abnormal navigation behaviors. The performance of the GPS-IDS framework is evaluated on the AV-GPS-Dataset -- a GPS security dataset for AVs comprising real-world data collected using an AV testbed, and simulated data representing urban traffic environments. To the best of our knowledge, this dataset is the first of its kind and has been publicly released for the global research community to address such security challenges.
Paper Structure (44 sections, 42 equations, 11 figures, 6 tables, 2 algorithms)

This paper contains 44 sections, 42 equations, 11 figures, 6 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Vehicle Models
  4. Physics-based Model
  5. Data-centric Model
  6. Intrusion Detection System (IDS)
  7. Cyber-attacks on Vehicles
  8. GNSS Security
  9. GPS Intrusion Detection System (GPS-IDS)
  10. Data Collection Module
  11. Vehicle System and GPS Receiver
  12. Onboard Data Storage
  13. Autonomous Vehicle Behavior Model
  14. Dynamic Bicycle Model
  15. Localization/ Navigation
  16. ...and 29 more sections

Figures (11)

  • Figure 1: GPS-IDS Architecture
  • Figure 2: Dynamic bicycle model of an autonomous vehicle in a 2-dimensional inertial frame
  • Figure 3: PID Cascade Control Architecture
  • Figure 4: Autonomous Vehicle Behavior Model
  • Figure 5: Hardware Architecture of the AVT
  • ...and 6 more figures