Towards a Reliable Machine Learning-Based Global Misbehavior Detection in C–ITS: Model Evaluation Approach

Global misbehavior detection in Cooperative Intelligent Transport Systems (C–ITS) is carried out by a central entity named Misbehavior Authority (MA). The detection is based on local misbehavior detection information sent by Vehicle’s On–Board Units (OBUs) and by Road–Side Units (RSUs) called Misbehavior Reports (MBRs) to the MA. By analyzing these Misbehavior Reports (MBRs), the MA is able to compute various misbehavior detection information. In this work, we propose and evaluate different Machine Learning (ML)-based solutions for the internal detection process of the MA. We show through extensive simulation and several detection metrics the ability of solutions to precisely identify different misbehavior types.

[1]  J. Friedman.  Stochastic gradient boosting , 2002 .

[2]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[4]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[5]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  A. Varga,et al.  THE OMNET++ DISCRETE EVENT SIMULATION SYSTEM , 2003 .

[7]  Frank Kargl,et al.  VeReMi: A Dataset for Comparable Evaluation of Misbehavior Detection in VANETs , 2018, SecureComm.

[8]  Prinkle Sharma,et al.  Integrating Plausibility Checks and Machine Learning for Misbehavior Detection in VANET , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[9]  Vijay Laxmi,et al.  Misbehavior Detection Based on Ensemble Learning in VANET , 2011, ADCONS.

[10]  Frank Kargl,et al.  Pseudonym Schemes in Vehicular Networks: A Survey , 2015, IEEE Communications Surveys & Tutorials.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Jonathan Petit,et al.  Physical layer plausibility checks for misbehavior detection in V2X networks , 2019, WiSec.

[13]  Tim Leinmüller,et al.  Survey on Misbehavior Detection in Cooperative Intelligent Transportation Systems , 2016, IEEE Communications Surveys & Tutorials.

[14]  Yi Qian,et al.  Misbehavior Detection using Machine Learning in Vehicular Communication Networks , 2019, ICC 2019 - 2019 IEEE International Conference on Communications (ICC).

[15]  Thomas Engel,et al.  Luxembourg SUMO Traffic (LuST) Scenario: 24 hours of mobility for vehicular networking research , 2015, 2015 IEEE Vehicular Networking Conference (VNC).

[16]  Pascal Urien,et al.  Misbehavior Reporting Protocol for C-ITS , 2018, 2018 IEEE Vehicular Networking Conference (VNC).

[17]  Pascal Urien,et al.  CaTch: A Confidence Range Tolerant Misbehavior Detection Approach , 2019, 2019 IEEE Wireless Communications and Networking Conference (WCNC).

[18]  Fuad A. Ghaleb,et al.  An effective misbehavior detection model using artificial neural network for vehicular ad hoc network applications , 2017, 2017 IEEE Conference on Application, Information and Network Security (AINS).

[19]  Daniel Krajzewicz,et al.  Recent Development and Applications of SUMO - Simulation of Urban MObility , 2012 .

[20]  Reinhard German,et al.  Bidirectionally Coupled Network and Road Traffic Simulation for Improved IVC Analysis , 2011, IEEE Transactions on Mobile Computing.

[21]  Vijay Laxmi,et al.  Machine Learning Approach for Multiple Misbehavior Detection in VANET , 2011, ACC.

[22]  Sorin A. Huss,et al.  A Novel Framework for Efficient Mobility Data Verification in Vehicular Ad-hoc Networks , 2012, Int. J. Intell. Transp. Syst. Res..