PAMPOS: Causal Transformer-based Trajectory Prediction for Attack-Agnostic Misbehavior Detection in V2X Networks
It provides an attack-agnostic misbehavior detection method for V2X networks, addressing the limitation of supervised schemes that fail against unseen attacks.
PAMPOS uses a causal transformer-decoder trained on benign V2X trajectories to detect misbehavior via anomaly scoring, achieving AUC up to 0.98 and F1 up to 0.95 across 19 attack types without requiring attack-labeled data.
Misbehavior detection in Vehicle-to-Everything (V2X) networks is a second line of defense against insider falsification attacks that cryptographic mechanisms alone cannot address. Existing learning-based Misbehavior Detection Schemes (MDSs) are supervised, requiring labeled attack samples at training time, thus failing to counter unseen falsification attacks. We present PAMPOS, a causal transformer-decoder trained on benign VeReMi++ trajectories to learn normal mobility patterns. At inference time, misbehavior is identified as a deviation from the model's next-step kinematic predictions using a top-K normalized anomaly scoring mechanism that localizes falsification to specific kinematic features, without requiring attack-labeled training data. We evaluate PAMPOS across all 19 attack types in VeReMi++ under rush-hour and afternoon scenarios, achieving Area Under the Curve (AUC) values of up to 0.98 and F1-scores of up to 0.95 for most attack categories.