Attention in Motion: Secure Platooning via Transformer-based Misbehavior Detection

2025-12-17

AI Summary

Malicious authenticated vehicles in platooning systems inject false motion data, jeopardizing system stability and driving safety. Conventional anomaly detection methods suffer from high false-positive rates and fail to capture complex spatiotemporal dependencies inherent in multi-vehicle coordination. To address this, we propose AIMformer—a lightweight spatiotemporal fusion Transformer. Its key contributions include: (i) a novel Precision-Focused loss function explicitly optimized for false-positive sensitivity; (ii) a global positional encoding scheme supporting dynamic topology changes; and (iii) vehicle-specific temporal offset encoding to enhance sequential modeling. The model is optimized for edge deployment via TensorFlow Lite, ONNX, and TensorRT. Extensive experiments across four controller types and diverse attack scenarios demonstrate ≥0.93 detection accuracy and sub-millisecond inference latency—enabling real-time operation on onboard units and roadside infrastructure.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Adversarial Attacks & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Vehicular platooning promises transformative improvements in transportation efficiency and safety through the coordination of multi-vehicle formations enabled by Vehicle-to-Everything (V2X) communication. However, the distributed nature of platoon coordination creates security vulnerabilities, allowing authenticated vehicles to inject falsified kinematic data, compromise operational stability, and pose a threat to passenger safety. Traditional misbehaviour detection approaches, which rely on plausibility checks and statistical methods, suffer from high False Positive (FP) rates and cannot capture the complex temporal dependencies inherent in multi-vehicle coordination dynamics. We present Attention In Motion (AIMformer), a transformer-based framework specifically tailored for real-time misbehaviour detection in vehicular platoons with edge deployment capabilities. AIMformer leverages multi-head self-attention mechanisms to simultaneously capture intra-vehicle temporal dynamics and inter-vehicle spatial correlations. It incorporates global positional encoding with vehicle-specific temporal offsets to handle join/exit maneuvers. We propose a Precision-Focused (BCE) loss function that penalizes FPs to meet the requirements of safety-critical vehicular systems. Extensive evaluation across 4 platoon controllers, multiple attack vectors, and diverse mobility scenarios demonstrates superior performance ($geq$ 0.93) compared to state-of-the-art baseline architectures. A comprehensive deployment analysis utilizing TensorFlow Lite (TFLite), Open Neural Network Exchange (ONNX), and TensorRT achieves sub-millisecond inference latency, making it suitable for real-time operation on resource-constrained edge platforms. Hence, validating AIMformer is viable for both in-vehicle and roadside infrastructure deployment.

Problem

• Detects misbehavior in vehicular platoons using transformer-based methods
• Addresses security vulnerabilities from falsified kinematic data in V2X communication
• Reduces false positives in real-time detection for safety-critical systems

Innovation

• Transformer-based real-time misbehavior detection for vehicular platoons
• Multi-head self-attention capturing temporal and spatial correlations
• Precision-focused loss function minimizing false positives for safety