# PAMPOS: Causal Transformer-based Trajectory Prediction for Attack-Agnostic Misbehavior Detection in V2X Networks

arXiv: https://arxiv.org/abs/2605.06833 · HTML: https://mlsanity.com/paper/2605.06833/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 28 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [VeReMi: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs](https://mlsanity.com/paper/1804.06701/) (2018)
- [A Survey on Machine Learning-based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks](https://mlsanity.com/paper/2201.10500/) (2022)
- [SECMACE: Scalable and Robust Identity and Credential Management Infrastructure in Vehicular Communication Systems](https://mlsanity.com/paper/1707.05518/) (2017)
- [AttentionGuard: Transformer-based Misbehavior Detection for Secure Vehicular Platoons](https://mlsanity.com/paper/2505.10273/) (2025)
- [Federated Learning for Misbehaviour Detection with Variational Autoencoders and Gaussian Mixture Models](https://mlsanity.com/paper/2405.09903/) (2024)
- [Attention in Motion: Secure Platooning via Transformer-based Misbehavior Detection](https://mlsanity.com/paper/2512.15503/) (2025)

## Abstract (arXiv)

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.