Simulation Framework for Misbehavior Detection in Vehicular Networks

Joseph Kamel (1) , Mohammad Raashid Ansari (2) , Jonathan Petit (2) , Arnaud Kaiser (1) , Ines Ben Jemaa (1) , Pascal Urien (3, 4, 5)

1 IRT SystemX
2 Qualcomm Technologies, Inc.
3 CCN - Cybersecurity for Communication and Networking
4 INFRES - Département Informatique et Réseaux
5 IP Paris - Institut Polytechnique de Paris

Cooperative Intelligent Transport Systems (C-ITS) is an ongoing technology that will change our driving experience in the near future. In such systems, vehicles and RoadSide Unit (RSU) cooperate by broadcasting V2X messages over the vehicular network. Safety applications use these data to detect and avoid dangerous situations on time. MisBehavior Detection (MBD) in C-ITS is an active research topic which consists of monitoring data semantics of the exchanged Vehicle-to-X communication (V2X) messages to detect and identify potential misbehaving entities. The detection process consists of performing plausibility and consistency checks on the received V2X messages. If an anomaly is detected, the entity may report it by sending a Misbehavior Report (MBR) to the Misbehavior Authority (MA). The MA will then investigate the event and decide to revoke the sender or not. In this paper, we present a MisBehavior Detection (MBD) simulation framework that enables the research community to develop, test, and compare MBD algorithms. We also demonstrate its capabilities by running example scenarios and discuss their results. Framework For Misbehavior Detection (F 2 MD) is open source and available for free on our github.

Mots clés: Cooperative Intelligent Transport Systems (C- ITS); MisBehavior Detection; V2X; Simulation

Domaines: Modélisation et simulation; Cryptographie et sécurité [cs.CR]; Machine Learning [stat.ML]; Intelligence artificielle [cs.AI]; Systèmes et contrôle [cs.SY]

Joseph Kamel, Mohammad Raashid Ansari, Jonathan Petit, Arnaud Kaiser, Ines Ben Jemaa, et al.. Simulation Framework for Misbehavior Detection in Vehicular Networks. IEEE Transactions on Vehicular Technology, 2020, IEEE Transactions on Vehicular Technology, 69 (6), pp.6631-6643. ⟨10.1109/TVT.2020.2984878⟩. ⟨hal-02527873⟩