Cybersecurity-Focused Anomaly Detection in Connected Autonomous Vehicles Using Machine Learning
Preprint
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, generating 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 utilized 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 offering ensemble-based predictions, which enhanced model interpretability and performance. The Random Forest model achieved an R2 of 0.9830, MAE of 5.746, and a 95th percentile anomaly threshold of 14.18, while the stacked LSTM model attained an R2 of 0.9998, MAE of 82.425, and a 95th percentile anomaly threshold of 265.63. These results demonstrate the models' effectiveness in accurately predicting vehicle trajectories and detecting anomalies in autonomous driving scenarios.Keywords
All Related Versions
- Version 1, 2025-06-28, ArXiv
- Published version: , 566.
This publication has 16 references indexed in Scilit:
- Time-Series Anomaly Detection in Automated Vehicles Using D-CNN-LSTM AutoencoderIEEE Transactions on Intelligent Transportation Systems, 2024
- Deep Learning-Based Anomaly Detection for Connected Autonomous Vehicles Using Spatiotemporal InformationIEEE Transactions on Intelligent Transportation Systems, 2023
- Deep Learning–Based Pavement Performance Modeling Using Multiple Distress Indicators and Road Work HistoryJournal of Transportation Engineering, Part B: Pavements, 2023
- A deep learning approach for imbalanced crash data in predicting highway-rail grade crossings accidentsReliability Engineering & System Safety, 2021
- Real-time signal-vehicle coupled control: An application of connected vehicle data to improve intersection safetyAccident Analysis & Prevention, 2021
- IncLSTM: Incremental Ensemble LSTM Model towards Time Series DataComputers and Electrical Engineering, 2021
- Impact Evaluation of Cyber-Attacks on Traffic Flow of Connected and Automated VehiclesIEEE Access, 2020
- Applying a random forest method approach to model travel mode choice behaviorTravel Behaviour and Society, 2019
- A Survey of the Connected Vehicle Landscape—Architectures, Enabling Technologies, Applications, and Development AreasIEEE Transactions on Intelligent Transportation Systems, 2017
- The Real-World Safety Potential of Connected Vehicle TechnologyTraffic Injury Prevention, 2015