This paper presents a guarded quantum-assisted Spiking Neural Network (SNN) model for anomaly detection in space-based Industrial IoT (IIoT) networks using the E91 Quantum Key Distribution (QKD) protocol for reinforced and secure communication. The model uses intertwined photon pairs to provide cryptographic security and network traffic into the classes divided as normal and anomalous. Empirical evidences show that SNN performs better than ANN and RNN with a maximum accuracy of 88.94%. The approaches in explainable AI (XAI), that include SHAP and LIME, are used to explain decisions by model, providing evaluations in the process of classification. The framework of optimization works to decrease the classification error, system latency, and quantum key deviations, which provides for resilient real-time security in resource-constrained environments. Further investigations in future include the federated learning along with hybrid neuromorphic architectures to eventually enhance acquired communication and anomaly detection in next-generation space-based IIoT systems.
This paper presents a guarded quantum-assisted Spiking Neural Network (SNN) model for anomaly detection in space-based Industrial IoT (IIoT) networks using the E91 Quantum Key Distribution (QKD) protocol for reinforced and secure communication. The model uses intertwined photon pairs to provide cryptographic security and network traffic into the classes divided as normal and anomalous. Empirical evidences show that SNN performs better than ANN and RNN with a maximum accuracy of 88.94%. The approaches in explainable AI (XAI), that include SHAP and LIME, are used to explain decisions by model, providing evaluations in the process of classification. The framework of optimization works to decrease the classification error, system latency, and quantum key deviations, which provides for resilient real-time security in resource-constrained environments. Further investigations in future include the federated learning along with hybrid neuromorphic architectures to eventually enhance acquired communication and anomaly detection in next-generation space-based IIoT systems.
The rapid expansion of the Internet of Things in critical industrial environments has significantly increased the attack surface, exposing systems to sophisticated cyber threats. Traditional pattern-based intrusion detection systems struggle to detect such advanced attacks, while deep learning approaches, despite achieving high detection accuracy, often suffer from high computational cost and latency, limiting their deployment in resource-constrained edge gateways. Quantum machine learning offers a promising alternative by enabling high-dimensional feature representation; however, current implementations are constrained by hardware noise, limited qubit availability and backend-dependent execution characteristics in the Noisy Intermediate-Scale Quantum era. To address these challenges, this paper proposes a Residual Hybrid Quantum-Classical Neural Network (RHQ-CNN) for efficient intrusion detection in Edge-Industrial Internet of Things (Edge-IIoT) environments under idealized quantum simulation conditions. The proposed framework employs a classical neural network encoder to compress high-dimensional network traffic into a compact latent representation suitable for quantum processing. A variational quantum circuit with serial data re-uploading is then utilised to model complex non-linear decision boundaries without increasing qubit requirements. In addition, a residual connection fuses classical and quantum representations to improve training stability and preserve latent feature information. The model is evaluated on the Edge-IIoTset dataset and achieves a test accuracy of 99.94%, with high weighted performance across the 15-class detection task, although the extremely low-sample Fingerprinting class remains comparatively more challenging. Additional controlled ablation, deployment-cost, and bootstrap confidence interval analyses demonstrate the test-set metric stability and computational trade-offs of the proposed architecture. These findings highlight the potential of hybrid quantum-classical models for next-generation cybersecurity in industrial IoT systems.
ABSTRACT The increasing complexity of smart grid IoT ecosystems demands security architectures capable of resisting quantum‐era threats, protecting data privacy, and scaling across large distributed infrastructures. This study introduces a novel hybrid security framework that integrates quantum cryptography, deep learning–based intrusion detection, and federated learning into a unified, high‐assurance design tailored for next‐generation smart grid environments. The architecture employs quantum key distribution (QKD) for secure key generation, an adaptive deep feature obfuscation layer to mitigate adversarial manipulation, and a privacy‐preserving federated learning pipeline that eliminates centralized data exposure. Simulation‐based evaluations demonstrate substantial performance gains, achieving a low quantum bit error rate (1.8%), high key‐generation throughput (4900 keys/s), low latency (18 ms), and intrusion detection accuracy of 98.7%, consistently outperforming conventional cryptographic and machine learning baselines. The framework further exhibits enhanced resilience against quantum‐based and adversarial attacks, with efficient performance maintained even under increasing network density. While real‐world deployment will require hardware‐in‐the‐loop validation and optimization for heterogeneous traffic conditions, the results indicate strong potential for securing future smart grid IoT infrastructures and supporting sustainable smart city applications.
The rapid growth of the Internet of Things (IoT) is transforming industries such as healthcare, transportation, and smart infrastructure, but it also amplifies critical concerns regarding data security, privacy, and device authentication. Traditional cryptographic mechanisms offer partial protection, yet they remain vulnerable to emerging quantum computing threats, posing significant risks to IoT systems. Addressing these challenges, this paper introduces FLQC-IoT, a novel security framework that integrates federated learning (FL) with quantum computing (QC) to provide robust, scalable, and future-ready protection. Unlike conventional centralized approaches, FLQC-IoT enables decentralized model training directly on IoT devices, safeguarding sensitive data from exposure. Quantum technologies are incorporated at multiple layers: quantum neural networks accelerate optimization tasks, while quantum key distribution and quantum homomorphic encryption ensure tamper-proof key exchange and secure communication. Furthermore, the framework adapts dynamically to emerging threats through real-time anomaly detection and distributed intelligence, significantly enhancing resilience. Experimental results demonstrate a 15.32 % reduction in computational overhead and a 21.45 % decrease in authentication rounds compared to state-of-the-art methods, highlighting the framework’s efficiency and practical readiness. These findings underscore the significance and transformative impact of FLQC-IoT, providing a scalable, privacy-preserving, and resilient approach to securing IoT networks across critical domains, including healthcare, university campus networks, smart infrastructure, and transportation.
The fast growth of Internet of Things (IoT) networks has heightened the demand for secure, scalable and energy efficient communications methods. Traditional cryptographic techniques are more susceptible to quantum computing attacks and therefore have pushed the necessity for quantum secure methods. This study presents an energy efficient artificial intelligence assisted quantum secure communication framework designed to scale and provide reliable IoT networks. The framework uses Quantum Key Distribution (QKD) combined with deep learning optimization to improve both relationship and network performance. A self-adaptive AI module applies its lower level of computational resources and dynamically changing network conditions in order to optimize key management, routing decisions, and resource allocation, which reduces both energy consumption and communication latency. The proposed system is intended to support the specific types of constraints faced within an IoT environment. The experimental simulation results demonstrate that the framework improves energy efficiency, increases packet delivery ratio, and decreases latency in IVN (Intelligent Vehicular Networks) by comparison with traditional means of secure communication. In addition, by combining AI and quantum communications, we increase our resilience to threats posed by both classical and quantum forms of attack while providing an added layer of protection for transmitting data between devices in future wireless networks. Additionally, this proposed framework will provide a very scalable and effective method for providing IoT solutions within the environment of 5G mobile networks or later generations.
Secure communication systems are increasingly challenged by advanced cyberattacks and the emerging impact of quantum computing. Existing security approaches rely on static encryption techniques and rigid decision mechanisms, which are insufficient to handle evolving threats and lack transparency in decision-making. To address these challenges, this paper proposes a framework that integrates Explainable Artificial Intelligence (XAI) with quantum-inspired cryptographic techniques for intelligent threat detection. The system utilizes a quantum-inspired simulation approach, based on the principles of Quantum Key Distribution (QKD), to generate and distribute secure session keys. Anomalies in communication are identified through key mismatches during transmission. A machine learning-based monitoring module analyzes parameters such as key match rate, error rate, and transmission delay to classify system behavior as normal, suspicious, or malicious. Additionally, an explainability component provides clear reasoning behind detection decisions using Permutation Feature Importance (PFI) to provide feature-level explanations for the model predictions, thereby enhancing transparency and user trust. Experimental evaluation on 8,000 simulated communication sessions demonstrates 98.69% detection accuracy with a false positive rate of 0.88%, with XAI explanations identifying transmission delay as the most influential feature, followed by the key mismatch rate and QBER, thereby providing interpretable insights into the factors contributing to threat detection and offering a scalable solution for next-generation secure communication systems.
The current security systems cannot be considered long term sustainable because there is a quantum rate of development of the computing which directly and immediately threatens the classical cryptograph systems. In this respect, the research paper will undertake efforts in giving the concept of an AI-led adaptive mechanism of Quantum Key Distribution (QKD) protocols that will be self-sufficient in guarding and overseeing quantum communication networks against countermeasures towards the constantly evolving threats. The model combines quantum resources management and real-time threat analysis and optimization of dynamic parameter into one flow. Quantum channel noises can be predictedively implemented on machine learning using reinforcement learning, continued intrusion and anomaly detection on neural networks, and independent optimization of the parameters of QKD in dynamical communication systems. Post-quantum cryptography PQC algorithm-based lattice, hash-based and multivariate cryptography are also provided in the system as a backup mechanism to provide the confidence of the hybrid communication environments with the future compatibility of the classical and quantum infrastructural systems. In other cases, the framework will enhance quantum- enhanced blockchain where the AI-enhanced verification enhances the integrity of the distributed registries and resilience in the interparty communication networks. The ethical considerations and the need to have light and interoperative standards are the other considerations since it needs to be able to deploy on a large scale. Instead of calculating the performance standards, the provided research involves the conceptual architecture diagram of the way the predictive AI models can be logically aligned with the natural security features of quantum mechanics to a new generation cryptographic ecosystem that will be able to fight the classical and the quantum adversaries simultaneously.