A carregar...
Publicação
Multi-Class Intrusion Detection in Internet of Vehicles: Optimizing Machine Learning Models on Imbalanced Data
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 274.05 KB | Adobe PDF |
Orientador(es)
Resumo(s)
The Internet of Vehicles (IoV) presents complex cybersecurity challenges, particularly against Denial-of-Service (DoS) and spoofing attacks targeting the Controller Area Network (CAN) bus. This study leverages the CICIoV2024 dataset, comprising six distinct classes of benign traffic and various types of attacks, to evaluate advanced machine learning techniques for instrusion detection systems (IDS). The models XGBoost, Random Forest, AdaBoost, Extra Trees, Logistic Regression, and Deep Neural Network were tested under realistic, imbalanced data conditions, ensuring that the evaluation reflects real-world scenarios where benign traffic dominates. Using hyperparameter optimization with Optuna, we achieved significant improvements in detection accuracy and robustness. Ensemble methods such as XGBoost and Random Forest consistently demonstrated superior performance, achieving perfect accuracy and macro-average F1-scores, even when detecting minority attack classes, in contrast to previous results for the CICIoV2024 dataset. The integration of optimized hyperparameter tuning and a broader methodological scope culminated in an IDS framework capable of addressing diverse attack scenarios with exceptional precision.
Descrição
Article number - 162
(This article belongs to the Special Issue Intrusion Detection and Resiliency in Cyber-Physical Systems and Networks)
(This article belongs to the Special Issue Intrusion Detection and Resiliency in Cyber-Physical Systems and Networks)
Palavras-chave
Cybersecurity Machine learning Imbalanced data Internet of vehicles (IoV) Intrusion detection system (IDS) Multi-class classification
Contexto Educativo
Citação
Palma, Á.; Antunes, M.; Bernardino, J.; Alves, A. Multi-Class Intrusion Detection in Internet of Vehicles: Optimizing Machine Learning Models on Imbalanced Data. Future Internet 2025, 17, 162. https:// doi.org/10.3390/fi17040162
Editora
MDPI