The increasing complexity of connected and 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 paper proposes EQAI—an Explainable Quantum Artificial Intelligence framework that fuses quantum-enhanced learning with interpretable trust inference for securing vehicular communications. The EQAI model employs an 8-qubit variational quantum circuit (VQC) integrated with lightweight classical layers and explainability modules based on SHAP and LIME. Using the CICIoV2024 dataset, 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, blockchain-based, and federated learning approaches. Its compact design—with only 4,900 trainable parameters and ∼19.5k 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.

Biochemical threats remain a serious concern in mission-critical environments, particularly those characterized by intermittent connectivity and infrastructure degradation. Traditional centralized detection systems are ill-suited for such conditions, as they depend on stable communication channels and are inherently vulnerable to cyber-physical disruptions. This work introduces a decentralized solution integrating Artificial Intelligence (AI) and blockchain (BC) for autonomous biochemical threat detection within tactical Mobile Ad-hoc Networks (MANETs). The framework uses a Random Forest (RF) classifier trained on acetylcholinesterase sensor data to identify sarin exposure with 100% accuracy and sub-25ms inference latency. Threat verification is secured using a lightweight Proof of Authority and Association (PoA2) BC, which provides tamper-resistant logging and distributed consensus. The architecture supports offline operations and maintains functionality under conditions of 20% packet loss and node disruption. Simulations conducted in degraded network environments confirmed the system’s robustness and scalability, establishing it as a resilient and efficient platform for secure biochemical threat detection in dynamic, resource-constrained mission-critical settings.

The Internet of Medical Things (IoMT) enables continuous health monitoring but still faces challenges in achieving personalized predictions and ensuring secure, tamper-proof data integrity. We presentRemoteCare, an AI-driven multi-modal framework that fuses synchronized physiological and network data for dual-task learning, simultaneously performing personalized health state classification (Normal, Warning, Critical) and cyberattack detection in IoMT traffic. Unlike conventional population-based thresholds,RemoteCaredynamically adapts alerts to each patient’s baseline, thereby minimizing false alarms and enhancing clinical reliability. A hybrid CNN–GRU–LSTM architecture jointly captures spatial and temporal dependencies across heterogeneous signals, while SHAP-based explainability provides transparent, patient-specific insights into the features influencing each prediction. To guarantee auditability, all predictions are immutably recorded on thePureChainblockchain integrated with IPFS, ensuring decentralized and tamper-proof storage. Evaluated on the WUSTL-EHMS-2020 dataset (Enhanced Healthcare Monitoring System),RemoteCareachieved 99.7% accuracy for health classification and 96.0% for intrusion detection, with negligible false alarms and efficient inference suitable for real-time deployment. By unifying multimodal prediction, personalization, interpretability, and secure logging,RemoteCareestablishes a trustworthy framework for early intervention, patient-specific risk assessment, and clinician-oriented decision support in remote healthcare.

Vulnerabilities in drone networks stem from the reliance on GPS and wireless communication technologies, combined with the lack of robust security mechanisms. This study proposes DroneGuard, a comprehensive cybersecurity framework leveraging supervised machine learning (ML) and explainable artificial intelligence (XAI) to detect intrusions and provide insights into the decision-making process of the security model. We explored various feature selection techniques to design a lightweight model suitable for the resource constraints of drones. Additionally, the synthetic minority oversampling technique (SMOTE) is employed to balance target class distribution and mitigate performance degradation, while randomized search cross-validation (RSCV) aids in selecting optimal hyperparameters for model training. Simulation experiments were conducted using a real-time GPS dataset for autonomous vehicles and a cybersecurity dataset containing variants of Denial of Service (DoS) attacks to evaluate the models’ performance. Comparison with four ML models using essential evaluation metrics validated the robust performance of the decision tree model, which detected spoofed GPS signals and DoS attacks with high accuracy, low-computational complexity, and minimal false alarm rates. Furthermore, the Shapley additive explanation (SHAP) provides intuitive visual explanations of important features contributing to the detection and classification of both GPS spoofing and DoS attacks. Therefore, DroneGuard offers effective and interpretable security solutions for enhanced drone application and adoption.

The intelligence and integrity of a real-time cyber–physical system depend on how trustworthy the data’s legitimacy, appropriation, and authorization are during end-to-end communication between the participating nodes in its network. With the recurrent repugnant global violations of the airspace by drones and their derivatives, there is an urgent need to empirically evaluate the underlying security architectures that govern drone usage operations for priority logistics. This review examines the significant contribution of artificial intelligence models and blockchain to the development of trustworthy and reliable intelligent and secure autonomous systems by integrating cyberspace, intelligence space, and airspace security. PRISMA-SPIDER methodology was adopted for the systematic review of 133 articles based on the inclusion criteria consisting of 91 (68.4%) quantitative studies, 19 qualitative studies (14.2%), and 23 (17.3%) mixed method studies to balance article selection sensitivity and specificity. The review outcome shows a significant disconnect between model proposals and actual implementation. Through the incorporation of zero-trust architecture into the existing blockchain technology and the convergence of newer AI models, dynamic security issues like drone ownership authentication, drone package delivery verification, drone operation authorization, and drone jurisdiction accountability, can be achieved seamlessly for secure smart mobility via drone transportation systems.

Achieving communication intelligence with a low computational cost is necessary for wireless sensor networks for the drone transportation system. This work proposed a novel localization system with low computational and time efficiency that uses an unmanned aerial vehicle (UAV) as anchor node and lightweight neural networks to evaluate the UAV position information. The scheme takes advantage of the capabilities of artificial intelligence models. Simulation results indicate that the proposed scheme displayed a good performance with the least localization error of 1.75, least training time of 0.0032s, and testing time of 0.00039s without requiring GPS when compared to other algorithms and previous schemes.

As unmanned aerial vehicles (UAVs) are progressively deployed for logistics purposes, there is need for paradigm shift from mere drone detection to proactive identification of the conveyed objects and proper risk assessment from a far distance. This paper proposed a timely, efficient, accurate, and situation-aware (TEAS) mission critical operation approach for detecting, localizing, and neutralizing UAVs under 3 scenarios (sunny, cloudy, and evening) and different altitudes using vision- based deep learning model. Two manually generated datasets consisting of 7200 samples from 6 UAV models and 3600 samples from 9 conveyed objects were used for simulation purposes. The proposed model was compared with 7 state-of-the-art models based on selected performance metrics. The results shows that the proposed model achieved superior mean average precision of 99.5%, 100% sensitivity, 11.2% specificity, 21.5% G-mean, and 99.8% F1-score with a latency of 0.021s, and throughput of 16.4 Gbps, which is better than other models. The model also exhibited high efficiency with cost noise at 0.037, and high reliability with minimal detection error which makes it suitable for mission critical operation of proactive and situation-aware countering of drones.