<![CDATA[The rapid development of the Internet of Vehicles (IoV) has significantly increased the exposure of intelligent transportation systems to sophisticated cyber threats, particularly targeting in-vehicle communication networks such as the Controller Area Network (CAN). Conventional intrusion detection systems and traditional machine learning approaches often face limitations in capturing complex attack patterns under high-dimensional and dynamic vehicular network conditions. To address these challenges, this paper proposes a Transformer-based intrusion detection framework for the Internet of Vehicles using a multi-strategy feature selection approach. The proposed method integrates Information Gain, Principal Component Analysis, and Random Forest-based feature importance to systematically identify the most informative features from vehicular network traffic while reducing redundancy and computational overhead. A Transformer architecture with a self-attention mechanism is employed to model global dependencies and complex interactions within CAN bus data. The framework is evaluated on the CICIoV dataset using multiple data representations, including binary, decimal, and hexadecimal formats, to reflect realistic IoV communication scenarios. Experimental results demonstrate that the proposed model achieves consistently high detection performance, with accuracy and F1-score exceeding 99% under optimal feature selection configurations, while maintaining stable generalization across cross-validation folds. These findings indicate that the proposed framework provides a robust and effective solution for intelligent intrusion detection in Internet of Vehicles networks. Unlike existing approaches that rely on single feature selection strategies or raw feature inputs, the proposed framework uniquely integrates three complementary selection techniques within a unified Transformer-based architecture, addressing both feature redundancy and model scalability simultaneously. The findings of this study have significant implications for cybersecurity in intelligent transportation systems, offering a scalable and computationally efficient intrusion detection solution applicable to resource-constrained vehicular edge devices such as Electronic Control Units.]]>
