CATS: A framework for Cooperative Autonomy Trust&Security

2025-03-01

AI Summary

To address the problem of erroneous situational awareness caused by malicious vehicles forging or tampering with shared perception data in vehicle-infrastructure cooperative systems, this paper proposes a lightweight security detection framework integrating dynamic reputation assessment and distributed majority consensus. The framework preserves vehicle privacy by jointly incorporating differential privacy protection and consistency verification, enabling low-latency, low-overhead identification and isolation of malicious nodes. Compared to conventional reputation-based or pure majority-voting approaches, our solution reduces communication overhead by over 40% while maintaining high detection accuracy and low false-positive rates. Extensive evaluation is conducted on a city-scale traffic simulation driven by real-world traffic data, demonstrating scalability to large-scale V2X deployments. The proposed framework establishes a novel paradigm for cooperative perception that simultaneously ensures security, privacy preservation, and system scalability.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Coordination and Collaboration

Application Category

• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

With cooperative perception, autonomous vehicles can wirelessly share sensor data and representations to overcome sensor occlusions, improving situational awareness. Securing such data exchanges is crucial for connected autonomous vehicles. Existing, automated reputation-based approaches often suffer from a delay between detection and exclusion of misbehaving vehicles, while majority-based approaches have communication overheads that limits scalability. In this paper, we introduce CATS, a novel automated system that blends together the best traits of reputation-based and majority-based detection mechanisms to secure vehicle-to-everything (V2X) communications for cooperative perception, while preserving the privacy of cooperating vehicles. Our evaluation with city-scale simulations on realistic traffic data shows CATS's effectiveness in rapidly identifying and isolating misbehaving vehicles, with a low false negative rate and overheads, proving its suitability for real world deployments.

Problem

• Securing data exchanges for autonomous vehicles
• Reducing delays in detecting misbehaving vehicles
• Minimizing communication overheads in V2X systems

Innovation

• Combines reputation-based and majority-based detection mechanisms
• Secures V2X communications for cooperative perception
• Ensures privacy and rapid misbehavior detection with low overhead