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.

The deployment of Internet of Things (IoT) devices requires efficient security mechanisms. However, cryptographic solutions often prove resource-intensive. Radio Frequency Fingerprinting (RFF) enables device authentication through the intrinsic characteristics of RF signals at the Physical (PHY)-layer. Deploying RFF presents two challenges: ensuring operational efficiency and scalability in resource -constrained environments. This paper presents a lightweight Edge AI -based RFF model for device authentication using PHY-layer characteristics. Our approach implements a Deep Learning (DL) model to extract device-specific features from IQ samples, converted using TensorFlow Lite for edge deployment. Evaluation on Raspberry Pi demonstrates high accuracy (> 0.95) and Receiver Operating Characteristic-Area Under the Curve (ROC-AUC) scores (> 0.90), while maintaining a compact model size suitable for resource-constrained environments.