Skip to main content
ICTD 2025 Main banner
Final Program


Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Back

ICTD 2025

Connected & Automated Vehicles (CAV) Impacts

POSTER RECEPTION (View list of posters here)

Cybersecurity-Focused Anomaly Detection in Connected Autonomous Vehicles Using Machine Learning

Tuesday, June 10, 2025
4:45 PM – 6:00 PM MT
Abstract: Anomaly detection in connected autonomous vehicles (CAVs) is crucial for maintaining safe and reliable transportation networks, as CAVs can be susceptible to sensor malfunctions, cyber-attacks, and unexpected environmental disruptions. This study explores an anomaly detection approach by simulating vehicle behavior, using a generalized form of the Intelligent Driver Model (IDM) to generate a dataset that represents typical and atypical vehicular interactions. The dataset includes time-series data of position, speed, and acceleration for multiple connected autonomous vehicles. We carried out a case study involving 10 connected vehicles and simulated a range of cyber-attacks to test the robustness of the anomaly detection system. We utilized a combination of deep learning and machine learning models to effectively identify abnormal driving patterns. First, we applied a stacked Long Short-Term Memory (LSTM) model to capture temporal dependencies and sequence-based anomalies. The stacked LSTM model processed the sequential data to learn standard driving behaviors. Additionally, we deployed a Random Forest model to support anomaly detection by providing ensemble-based predictions, which enhanced model interpretability and performance. The proposed models demonstrated strong anomaly identification capabilities, effectively distinguishing between standard and abnormal vehicle behavior, even in the presence of simulated cyber-attacks. The results of the modeling confirm that the approach is well-suited to detect anomalies in CAV behavior, contributing to safer and more reliable transportation systems.

Learning Objectives:

Attendees can expect to learn the following from this session:
  • Upon completion, participants will be able to define key concepts and terminology related to anomaly detection in connected autonomous vehicles.
  • Upon completion, participants will be able to describe the process of simulating vehicle behavior using a generalized form of the Intelligent Driver Model (IDM).
  • Upon completion, participants will be able to demonstrate the use of machine learning models, such as LSTM and Random Forest, to identify anomalies in time-series data of connected autonomous vehicles.