Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A neural-network based anomaly detection system and a safety protocol to protect vehicular network

Marco Franceschini

TL;DR

A Machine Learning-based Misbehavior Detection System (MDS) using Long Short-Term Memory (LSTM) networks to detect and mitigate incorrect or misleading messages within vehicular networks to improve road safety and efficiency.

Abstract

This thesis addresses the use of Cooperative Intelligent Transport Systems (CITS) to improve road safety and efficiency by enabling vehicle-to-vehicle communication, highlighting the importance of secure and accurate data exchange. To ensure safety, the thesis proposes a Machine Learning-based Misbehavior Detection System (MDS) using Long Short-Term Memory (LSTM) networks to detect and mitigate incorrect or misleading messages within vehicular networks. Trained offline on the VeReMi dataset, the detection model is tested in real-time within a platooning scenario, demonstrating that it can prevent nearly all accidents caused by misbehavior by triggering a defense protocol that dissolves the platoon if anomalies are detected. The results show that while the system can accurately detect general misbehavior, it struggles to label specific types due to varying traffic conditions, implying the difficulty of creating a universally adaptive protocol. However, the thesis suggests that with more data and further refinement, this MDS could be implemented in real-world CITS, enhancing driving safety by mitigating risks from misbehavior in cooperative driving networks.

A neural-network based anomaly detection system and a safety protocol to protect vehicular network

TL;DR

A Machine Learning-based Misbehavior Detection System (MDS) using Long Short-Term Memory (LSTM) networks to detect and mitigate incorrect or misleading messages within vehicular networks to improve road safety and efficiency.

Abstract

This thesis addresses the use of Cooperative Intelligent Transport Systems (CITS) to improve road safety and efficiency by enabling vehicle-to-vehicle communication, highlighting the importance of secure and accurate data exchange. To ensure safety, the thesis proposes a Machine Learning-based Misbehavior Detection System (MDS) using Long Short-Term Memory (LSTM) networks to detect and mitigate incorrect or misleading messages within vehicular networks. Trained offline on the VeReMi dataset, the detection model is tested in real-time within a platooning scenario, demonstrating that it can prevent nearly all accidents caused by misbehavior by triggering a defense protocol that dissolves the platoon if anomalies are detected. The results show that while the system can accurately detect general misbehavior, it struggles to label specific types due to varying traffic conditions, implying the difficulty of creating a universally adaptive protocol. However, the thesis suggests that with more data and further refinement, this MDS could be implemented in real-world CITS, enhancing driving safety by mitigating risks from misbehavior in cooperative driving networks.

Paper Structure

This paper contains 50 sections, 1 equation, 39 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Thesis Goals
  3. Thesis Structure
  4. Related work
  5. Security and Privacy in Vehicular Networks
  6. Standardization
  7. Privacy management
  8. Studied attacks on Cooperative Adaptive Cruise Control
  9. Achievement
  10. Misbehavior detection systems literature
  11. Long Short-Term Memory systems
  12. Reinforcement Learning
  13. Federated Learning
  14. On-line simulations approach
  15. Achievement
  16. ...and 35 more sections

Figures (39)

  • Figure 1: How many vehicles change their type (regular or misbehavior) during the VeReMi constant position offset simulation
  • Figure 2: Subfolders' structure of the VeReMi dataset
  • Figure 3: Structure of a message in the log files
  • Figure 4: Representation of the data merging between the log files and the ground truth.
  • Figure 5: Structure of the final data frame saved for each scenario type
  • ...and 34 more figures