Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MIXED-SENSE: A Mixed Reality Sensor Emulation Framework for Test and Evaluation of UAVs Against False Data Injection Attacks

Kartik A. Pant, Li-Yu Lin, Jaehyeok Kim, Worawis Sribunma, James M. Goppert, Inseok Hwang

TL;DR

The paper addresses the challenge of evaluating UAV resilience to false data injection attacks, especially GNSS spoofing, in a safe and realistic setting. It presents a Mixed Reality-in-the-Loop sensor emulation framework that fuses Gazebo-based physics with Motion Capture to emulate both proprioceptive and exteroceptive sensors in real time, including latency and noise characteristics. The authors demonstrate the approach through a GNSS meaconing attack on an actual UAV and validate a mitigation strategy using a distributed camera network for external measurements and a linear observer-based detector. An open-source implementation is released at GitHub, enabling end-to-end cybersecurity testing for single UAVs and swarms. The framework promises to improve fidelity and safety for UAV cybersecurity evaluation and can support future swarm-scale experiments.

Abstract

We present a high-fidelity Mixed Reality sensor emulation framework for testing and evaluating the resilience of Unmanned Aerial Vehicles (UAVs) against false data injection (FDI) attacks. The proposed approach can be utilized to assess the impact of FDI attacks, benchmark attack detector performance, and validate the effectiveness of mitigation/reconfiguration strategies in single-UAV and UAV swarm operations. Our Mixed Reality framework leverages high-fidelity simulations of Gazebo and a Motion Capture system to emulate proprioceptive (e.g., GNSS) and exteroceptive (e.g., camera) sensor measurements in real-time. We propose an empirical approach to faithfully recreate signal characteristics such as latency and noise in these measurements. Finally, we illustrate the efficacy of our proposed framework through a Mixed Reality experiment consisting of an emulated GNSS attack on an actual UAV, which (i) demonstrates the impact of false data injection attacks on GNSS measurements and (ii) validates a mitigation strategy utilizing a distributed camera network developed in our previous work. Our open-source implementation is available at \href{https://github.com/CogniPilot/mixed\_sense}{\texttt{https://github.com/CogniPilot/mixed\_sense}}

MIXED-SENSE: A Mixed Reality Sensor Emulation Framework for Test and Evaluation of UAVs Against False Data Injection Attacks

TL;DR

The paper addresses the challenge of evaluating UAV resilience to false data injection attacks, especially GNSS spoofing, in a safe and realistic setting. It presents a Mixed Reality-in-the-Loop sensor emulation framework that fuses Gazebo-based physics with Motion Capture to emulate both proprioceptive and exteroceptive sensors in real time, including latency and noise characteristics. The authors demonstrate the approach through a GNSS meaconing attack on an actual UAV and validate a mitigation strategy using a distributed camera network for external measurements and a linear observer-based detector. An open-source implementation is released at GitHub, enabling end-to-end cybersecurity testing for single UAVs and swarms. The framework promises to improve fidelity and safety for UAV cybersecurity evaluation and can support future swarm-scale experiments.

Abstract

We present a high-fidelity Mixed Reality sensor emulation framework for testing and evaluating the resilience of Unmanned Aerial Vehicles (UAVs) against false data injection (FDI) attacks. The proposed approach can be utilized to assess the impact of FDI attacks, benchmark attack detector performance, and validate the effectiveness of mitigation/reconfiguration strategies in single-UAV and UAV swarm operations. Our Mixed Reality framework leverages high-fidelity simulations of Gazebo and a Motion Capture system to emulate proprioceptive (e.g., GNSS) and exteroceptive (e.g., camera) sensor measurements in real-time. We propose an empirical approach to faithfully recreate signal characteristics such as latency and noise in these measurements. Finally, we illustrate the efficacy of our proposed framework through a Mixed Reality experiment consisting of an emulated GNSS attack on an actual UAV, which (i) demonstrates the impact of false data injection attacks on GNSS measurements and (ii) validates a mitigation strategy utilizing a distributed camera network developed in our previous work. Our open-source implementation is available at \href{https://github.com/CogniPilot/mixed\_sense}{\texttt{https://github.com/CogniPilot/mixed\_sense}}
Paper Structure (11 sections, 1 equation, 5 figures)

This paper contains 11 sections, 1 equation, 5 figures.

Table of Contents

  1. Introduction
  2. Related Works
  3. Mixed Reality in Robotics
  4. Testbed for UAV Cybersecurity
  5. Mixed Reality Sensor Emulation
  6. Latency in Sensor Emulation
  7. Experimental Demonstration
  8. GNSS Meaconing Attacks
  9. Distributed Camera Network
  10. Offboard Attack Detector
  11. Conclusion

Figures (5)

  • Figure 1: An instance of Mixed-Reality-in-the-loop (MRiTL) GNSS sensor emulation
  • Figure 2: Overview of our proposed framework. Gazebo's rendering engine spawns real vehicles tracked in the motion capture and virtual vehicles running as PX4 SiTL instances. Gazebo's physics engine performs the real-time processing of scene rendering, sensor emulation, and collision detection.
  • Figure 3: End-to-end time delay from sensing the motion of the real vehicle to publishing the emulated sensor measurements.
  • Figure 4: Empirical latency in each component and total end-to-end latency in GNSS sensor emulation
  • Figure 5: Application of the proposed framework for test and validation of UAVs: Assessing the impacts of GNSS Meaconing attacks on the actual vehicle, and validating the use of external measurements for attack detection and mitigation.