Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CONClave -- Secure and Robust Cooperative Perception for CAVs Using Authenticated Consensus and Trust Scoring

Edward Andert, Francis Mendoza, Hans Walter Behrens, Aviral Shrivastava

TL;DR

Overall, CONClave shows huge promise in preventing security flaws, detecting even relatively minor sensing faults, and increasing the robustness and accuracy of cooperative perception in CAVs while adding minimal overhead.

Abstract

Connected Autonomous Vehicles have great potential to improve automobile safety and traffic flow, especially in cooperative applications where perception data is shared between vehicles. However, this cooperation must be secured from malicious intent and unintentional errors that could cause accidents. Previous works typically address singular security or reliability issues for cooperative driving in specific scenarios rather than the set of errors together. In this paper, we propose CONClave, a tightly coupled authentication, consensus, and trust scoring mechanism that provides comprehensive security and reliability for cooperative perception in autonomous vehicles. CONClave benefits from the pipelined nature of the steps such that faults can be detected significantly faster and with less compute. Overall, CONClave shows huge promise in preventing security flaws, detecting even relatively minor sensing faults, and increasing the robustness and accuracy of cooperative perception in CAVs while adding minimal overhead.

CONClave -- Secure and Robust Cooperative Perception for CAVs Using Authenticated Consensus and Trust Scoring

TL;DR

Overall, CONClave shows huge promise in preventing security flaws, detecting even relatively minor sensing faults, and increasing the robustness and accuracy of cooperative perception in CAVs while adding minimal overhead.

Abstract

Connected Autonomous Vehicles have great potential to improve automobile safety and traffic flow, especially in cooperative applications where perception data is shared between vehicles. However, this cooperation must be secured from malicious intent and unintentional errors that could cause accidents. Previous works typically address singular security or reliability issues for cooperative driving in specific scenarios rather than the set of errors together. In this paper, we propose CONClave, a tightly coupled authentication, consensus, and trust scoring mechanism that provides comprehensive security and reliability for cooperative perception in autonomous vehicles. CONClave benefits from the pipelined nature of the steps such that faults can be detected significantly faster and with less compute. Overall, CONClave shows huge promise in preventing security flaws, detecting even relatively minor sensing faults, and increasing the robustness and accuracy of cooperative perception in CAVs while adding minimal overhead.
Paper Structure (10 sections, 1 equation, 3 figures, 1 table, 2 algorithms)

This paper contains 10 sections, 1 equation, 3 figures, 1 table, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Our Approach
  4. Overview
  5. Three Party Authentication
  6. Single-shot Consensus
  7. Accurate Trust Scoring
  8. Experimental Setup
  9. Results
  10. Conclusion

Figures (3)

  • Figure 1: Overview of CONClave. Consensus and Authentication steps occur concurrently to reach a sensor data set that all participant CAVs and CISs agree upon. The sensor data set is then taken as input to our cooperative perception and trust scoring steps resulting in trust scores for each participant.
  • Figure 2: Four one-tenth scale CAVs with IMX160 camera, Slamware M1M1 LIDAR, and Nvidia Jetson Nano for on-board processing along with two one-tenth scale CIS traffic cameras using Jetson Nano and IMX160 camera test setup.
  • Figure :