Deep reinforcement learning improves vehicle misbehavior detection with missing data
Deep Reinforcement Learning for Misbehavior Detection Under Partially Observable V2X Data
Networking and Internet Architecture
Summary
Vehicles communicate with each other and infrastructure for safety, but some messages might be false or misleading. Detecting these bad messages is hard when some information is missing due to signal problems or obstacles. The researchers studied ways to teach computers to spot these false messages even with incomplete data. They found that using deep reinforcement learning works better than traditional methods, but it can still be fooled if attackers cleverly hide information.
What this means in practice
- •For vehicle system developers: Detect falsified vehicle-to-everything messages more accurately despite missing or incomplete communication data.
- •For network security teams: Design vehicle network defenses that handle strategic evasion tactics exploiting signal loss or missing information.
Authors
Roshan Sedar, Charalampos Kalalas
Abstract
Misbehavior detection in vehicle-to-everything (V2X) systems is essential for ensuring the semantic correctness of exchanged messages and preventing the dissemination of falsified information. Existing data-centric misbehavior detection approaches largely rely on statistical validation or supervised machine learning models under the implicit assumption of fully observable V2X streams. In practice, however, vehicular environments are inherently partially observable due to hardware failures, intermittent connectivity, and environmental occlusions. Moreover, missingness itself can be strategically exploited by adversaries to evade detection. In this paper, we study misbehavior detection under incomplete V2X observations and propose a deep reinforcement learning (DRL)-based detection framework that learns adaptive policies with incomplete data. We further introduce an adversarial threat model in which attackers exploit or deliberately induce missingness to evade detection, including evasion via natural occlusions and adversarial feature suppression. Extensive experiments conducted on the VeReMi dataset under various missingness patterns demonstrate that DRL significantly outperforms a powerful XGBoost baseline under natural partial observability. However, results also reveal a critical vulnerability: DRL policies can be highly susceptible to evasion attacks that strategically exploit natural missingness. In contrast, DRL exhibits more gradual degradation under direct feature suppression compared to static tree-based models.