Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Cyberattack Detection-Isolation Scheme For CAV Under Changing Driving Environment

Sanchita Ghosh, Nutan Saha, Tanushree Roy

TL;DR

The results show that the proposed algorithm can enhance the cybersecurity of CAVs by detecting cyberattacks on CAV platoons and isolating infrastructure-level traffic manipulation.

Abstract

Under a changing driving environment, a Connected Autonomous Vehicle (CAV) platoon relies strongly on the acquisition of accurate traffic information from neighboring vehicles as well as reliable commands from a centralized supervisory controller through the communication network. Even though such modalities are imperative to ensure the safe and efficient driving performance of CAVs, they led to multiple security challenges. Thus, a cyberattack on this network can corrupt vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, which can lead to unsafe or undesired driving scenarios. Hence, in this paper, we propose a cyberattack detection-isolation algorithm comprised of a unified V2V and V2I cyberattack detection scheme along with a V2I isolation scheme for CAVs under changing driving conditions. The proposed algorithm is constructed using a bank of residual generators with Lyapunov function-based performance guarantees, such as disturbance-to-state stability, robustness, and sensitivity. Finally, we showcase the efficacy of our proposed algorithm through extensive Monte-Carlo simulations using real-world highway and urban driving data. The results show that the proposed algorithm can enhance the cybersecurity of CAVs by detecting cyberattacks on CAV platoons and isolating infrastructure-level traffic manipulation.

A Cyberattack Detection-Isolation Scheme For CAV Under Changing Driving Environment

TL;DR

The results show that the proposed algorithm can enhance the cybersecurity of CAVs by detecting cyberattacks on CAV platoons and isolating infrastructure-level traffic manipulation.

Abstract

Under a changing driving environment, a Connected Autonomous Vehicle (CAV) platoon relies strongly on the acquisition of accurate traffic information from neighboring vehicles as well as reliable commands from a centralized supervisory controller through the communication network. Even though such modalities are imperative to ensure the safe and efficient driving performance of CAVs, they led to multiple security challenges. Thus, a cyberattack on this network can corrupt vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, which can lead to unsafe or undesired driving scenarios. Hence, in this paper, we propose a cyberattack detection-isolation algorithm comprised of a unified V2V and V2I cyberattack detection scheme along with a V2I isolation scheme for CAVs under changing driving conditions. The proposed algorithm is constructed using a bank of residual generators with Lyapunov function-based performance guarantees, such as disturbance-to-state stability, robustness, and sensitivity. Finally, we showcase the efficacy of our proposed algorithm through extensive Monte-Carlo simulations using real-world highway and urban driving data. The results show that the proposed algorithm can enhance the cybersecurity of CAVs by detecting cyberattacks on CAV platoons and isolating infrastructure-level traffic manipulation.
Paper Structure (18 sections, 1 theorem, 41 equations, 7 figures, 2 tables)

This paper contains 18 sections, 1 theorem, 41 equations, 7 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Literature And Contribution
  3. Problem Formulation
  4. Closed-loop vehicle dynamics
  5. Cyberattack policy and compromised platoon dynamics
  6. Cyberattack detection-isolation algorithm
  7. V2X Detection Scheme
  8. V2X detector dynamics
  9. Error dynamics and V2X DS residual generation
  10. Detector gain design
  11. V2X attack decision and V2I IS activator
  12. V2I Isolation Scheme
  13. Simulation Results
  14. Replay attack on single vehicle through V2V network
  15. FDI attack on single vehicle through V2I network
  16. ...and 3 more sections

Key Result

Theorem 1

Let us consider the vehicle platoon dynamics zeta and the V2X detector dynamics chihat. The $i^{th}$ detector is considered DSS, robust to uncertainty, and sensitive to cyberattacks for every mode $\alpha$, if there exists a set of positive symmetric matrices $\mathcal{P} := \{ {P_\alpha} : \alpha \ where $\Lambda_{2_{\alpha i}},\mathcal{G}_1,\mathcal{B}_{1_{\alpha i}},\mathcal{G}_2, \mathcal{B}_{

Figures (7)

  • Figure 1: Block diagram of the vehicle platoon.
  • Figure 2: Objectives of the adversary.
  • Figure 3: Schematic block diagram of the detection-isolation algorithm.
  • Figure 4: Under V2V cyberattack, the plot shows (top) the velocity, (second) the position, (third) the V2X DS residual, and (last) the V2I IS residual.
  • Figure 5: Under V2I cyberattack, the plot shows (top) the velocity, (second) the position, (third) the V2X DS residual, and (last) the V2I IS residual.
  • ...and 2 more figures

Theorems & Definitions (5)

  • Remark 1
  • Remark 2
  • Theorem 1
  • proof
  • Remark 3