AttentionGuard: Transformer-based Misbehavior Detection for Secure Vehicular Platoons

2025-05-15

AI Summary

Certified insider attackers in vehicle-infrastructure cooperative platooning can launch motion-state spoofing attacks—including constant, progressive, and hybrid variants—compromising system safety. Method: This paper proposes a real-time anomaly detection framework based on a lightweight multi-head self-attention mechanism. It introduces a streamlined Transformer encoder—novel for onboard security monitoring—fusing temporal kinematic data with V2X communication context features to generalize across diverse operational scenarios (e.g., steady-state cruising, merging, and lane departure). Contribution/Results: The framework achieves sub-100 ms inference latency and operates without reliance on predefined attack patterns. Evaluated under multi-controller, multi-speed, and multi-attack-location simulations, it attains an F1-score of 0.95, demonstrating significantly superior robustness over LSTM, CNN, and statistical baseline methods.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Planning, Routing, and Scheduling: Planning with Language Models
• Application Domains: Mobility, Driving & Flight

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Vehicle platooning, with vehicles traveling in close formation coordinated through Vehicle-to-Everything (V2X) communications, offers significant benefits in fuel efficiency and road utilization. However, it is vulnerable to sophisticated falsification attacks by authenticated insiders that can destabilize the formation and potentially cause catastrophic collisions. This paper addresses this challenge: misbehavior detection in vehicle platooning systems. We present AttentionGuard, a transformer-based framework for misbehavior detection that leverages the self-attention mechanism to identify anomalous patterns in mobility data. Our proposal employs a multi-head transformer-encoder to process sequential kinematic information, enabling effective differentiation between normal mobility patterns and falsification attacks across diverse platooning scenarios, including steady-state (no-maneuver) operation, join, and exit maneuvers. Our evaluation uses an extensive simulation dataset featuring various attack vectors (constant, gradual, and combined falsifications) and operational parameters (controller types, vehicle speeds, and attacker positions). Experimental results demonstrate that AttentionGuard achieves up to 0.95 F1-score in attack detection, with robust performance maintained during complex maneuvers. Notably, our system performs effectively with minimal latency (100ms decision intervals), making it suitable for real-time transportation safety applications. Comparative analysis reveals superior detection capabilities and establishes the transformer-encoder as a promising approach for securing Cooperative Intelligent Transport Systems (C-ITS) against sophisticated insider threats.

Problem

• Detect falsification attacks in vehicle platooning systems
• Identify anomalous mobility patterns using transformer-based framework
• Ensure real-time security against insider threats in C-ITS

Innovation

• Transformer-based framework for misbehavior detection
• Multi-head transformer-encoder processes kinematic data
• Real-time detection with minimal latency (100ms)