EQAI: Explainable Quantum-Empowered Antispoofing Intelligence for Trustworthy Connected Autonomous Vehicles Communication

초록

The increasing complexity of connected autonomous vehicles (CAVs) introduces new security challenges in the Internet of Vehicles (IoV), where traditional detection models struggle with real-time interpretability, scalability, and robustness against spoofing attacks. This article proposes an explainable quantum-empowered antispoofing intelligence (EQAI) framework that fuses quantum-enhanced learning with interpretable trust inference for securing vehicular communications. The EQAI model employs an eight-qubit variational quantum circuit (VQC) integrated with lightweight classical layers and explainability modules based on Shapley additive explanation (SHAP) and local interpretable model-agnostic explanation (LIME). Using Canadian Institute for Cybersecurity Internet of Vehicles 2024 Dataset (CICIoV2024), the framework achieves a detection accuracy of 92.85%, a Class 3 F1-score of 82.1%, and a low false alarm rate (FAR <= 0.026), outperforming existing machine learning (ML), blockchain (BC)-based, and federated learning (FL) approaches. Its compact design-with only 4900 trainable parameters and similar to 19.5 k floating point operations per second (FLOPs)-demonstrates real-time deployability and energy efficiency at the network edge. Moreover, LIME and SHAP analyses reveal transparent feature-level reasoning, enhancing operator trust and system explainability. The proposed EQAI architecture thus establishes a scalable, interpretable, and quantum-empowered foundation for secure, trustworthy, and intelligent vehicular networks, advancing toward resilient IoV and next-generation cybercognitive mobility ecosystems.

키워드