Abstract The secure distribution of keys is essential to ensuring the privacy and integrity of data in Internet of Things (IoT) systems. Quantum Key Distribution (QKD) protocols, such as BB84, use principles from quantum mechanics to establish secure communication channels. However, errors that occur during the transmission of qubits can compromise the reliability of the shared key. This paper presents a new method for error correction that integrates Convolutional Neural Networks (CNNs) into the BB84 protocol for QKD in IoT systems. By harnessing the exceptional pattern recognition capabilities of CNNs, our approach learns hierarchical representations from preprocessed quantum channel data to effectively identify and correct errors. Extensive simulations demonstrate the high performance of our CNN-based method in reducing the Quantum Bit Error Rate (QBER). This contribution significantly enhances the security and reliability of key distribution, offering a promising solution for robust quantum communication in IoT environments.
Abstract The secure distribution of keys is essential to ensuring the privacy and integrity of data in Internet of Things (IoT) systems. Quantum Key Distribution (QKD) protocols, such as BB84, use principles from quantum mechanics to establish secure communication channels. However, errors that occur during the transmission of qubits can compromise the reliability of the shared key. This paper presents a new method for error correction that integrates Convolutional Neural Networks (CNNs) into the BB84 protocol for QKD in IoT systems. By harnessing the exceptional pattern recognition capabilities of CNNs, our approach learns hierarchical representations from preprocessed quantum channel data to effectively identify and correct errors. Extensive simulations demonstrate the high performance of our CNN-based method in reducing the Quantum Bit Error Rate (QBER). This contribution significantly enhances the security and reliability of key distribution, offering a promising solution for robust quantum communication in IoT environments.
Quantum Key Distribution (QKD) enables information-theoretic secure key exchange by exploiting fundamental quantum phenomena such as superposition and no-cloning. Classical QKD protocols (e.g., BB84) guarantee that any eavesdropping attempt introduces detectable disturbances, but they typically assume stable, high-quality channels and unconstrained devices. In contrast, Internet of Things (IoT) networks present a radically different environment: devices have limited processing power, minimal onboard memory, strict energy budgets, and communicate over highly variable wireless links subject to interference and rapid fading. These constraints lead to elevated quantum bit error rates (QBER), frequent key reconciliation failures, and prohibitive energy costs, all of which jeopardize practical QKD deployment. To address these challenges, we propose an AI-powered QKD protocol specifically optimized for IoT scenarios. Our approach integrates three AI modules: (1) a gradient-boosted regression channel estimator that predicts instantaneous link transmittance using lightweight sensor data and historical photon counts; (2) a reinforcement learning (RL) agent that adaptively tunes photon intensity, basis-selection probability, and reconciliation block size to balance key rate and error rate; and (3) a convolutional neural network (CNN) classifier that selects the optimal Low-Density Parity-Check (LDPC) code rate based on real-time noise characteristics. We simulate a star-topology IoT network of 50 battery-powered devices communicating over 5 km polarization-encoded links with realistic urban loss (0.1–0.3 dB/km) and environmental noise. Compared against a static BB84 baseline, our AI-enhanced protocol reduces average QBER from 4.5% to 2.9%, increases secure key rate from 12.5 kbps to 16.0 kbps, lowers latency by 22%, and reduces energy consumption per key bit by 18%. These improvements persist across channel conditions and device heterogeneity, demonstrating robustness.
The Internet of Things (IoT) has experienced rapid growth, resulting in a proliferation of interconnected devices in domains such as smart homes, cities, and healthcare applications. Ensuring secure communication within IoT networks is crucial for protecting privacy and data. The BB84 protocol, a quantum key distribution (QKD) protocol, shows promise in enhancing IoT communication security. This paper presents a comprehensive security analysis of the BB84 protocol in IoT networks, examining key aspects including entropy, execution time, quantum bit error rate (QBER), and cryptographic key generation efficiency. The analysis aims to evaluate the protocol's resilience against potential attacks and its suitability for securing IoT communications. We delve into the evaluation of entropy levels in the key generation process to ensure strong cryptographic properties. We also examine the correlation between execution time and QBER to determine the protocol's efficiency and ability to counter timing-based attacks. Additionally, we analyze the efficiency of the keys generated by the BB84 protocol, taking into consideration factors such as key size, generation rate, and computational overhead. These evaluations allow us to assess the protocol's suitability for resource-constrained IoT devices
Quantum Key Distribution (QKD) is a pivotal technology in the quest for secure communication, harnessing the power of quantum mechanics to ensure robust data protection. However, scaling QKD to meet the demands of high-speed, real-world applications remains a significant challenge. Traditional key rate determination methods, dependent on complex mathematical models, often fall short in efficiency and scalability. In this paper, we propose an approach that involves integrating machine learning (ML) techniques with the Cascade error correction protocol to enhance the scalability and efficiency of QKD systems. Our ML-based approach utilizes an autoencoder framework to predict the Quantum Bit Error Rate (QBER) and final key length with over 99\% accuracy. This method significantly reduces error correction time, maintaining a consistently low computation time even with large input sizes, such as data rates up to 156 Mbps. In contrast, traditional methods exhibit exponentially increasing computation times as input sizes grow, highlighting the superior scalability of our ML-based solution. Through comprehensive simulations, we demonstrate that our method not only accelerates the error correction process but also optimizes resource utilization, making it more cost-effective and practical for real-world deployment. The Cascade protocol's integration further enhances system security by dynamically adjusting error correction based on real-time QBER observations, providing robust protection against potential eavesdropping. Our research establishes a new benchmark for scalable, high-throughput QKD systems, proving that machine learning can significantly advance the field of quantum cryptography. This work continues the evolution towards truly scalable quantum communication.
This paper analyzes the performance of two quantum key distribution (QKD) protocols, SARG04 and BB84, under different random quantum noise levels. It also looks at the protocols’ potential applications in Internet of Things (IoT) device security for a proposed architecture. In the proposed model, long-range photons are inherently vulnerable to quantum noise, which complicates real-world QKD implementations and jeopardizes the reliability and resilience of the secret key generation process. By simulating different noise situations, we evaluate the overall security performance, mistake rates, and key generation rates of the BB84 and SARG04 protocols. Our findings suggest that although both protocols can withstand moderate noise levels, SARG04 and BB84 perform similarly regarding secure key length. We also address the consequences of these results for the security of the Internet of Things, highlighting QKD’s role in minimizing vulnerabilities related to conventional cryptography techniques. QKD integration can improve data security and privacy in Internet of Things frameworks, offering a viable way to protect sensitive data in increasingly networked devices. This work significantly contributes to the current efforts in quantum cryptography research by providing insightful advice on protocol selection and secure IoT connectivity implementation techniques.
Quantum Key Distribution (QKD) leverages quantum mechanical principles to establish information-theoretically secure cryptographic keys. The cornerstone BB84 protocol, however, suffers from key rate degradation due to the mandatory discarding of erroneous bits during post-processing. This paper presents an enhanced BB84 protocol incorporating a Tagging and Correction Method that systematically tracks, classifies, and corrects errors rather than discarding them. This approach maximizes the key material retained from the quantum transmission. The protocol integrates decoy state analysis for robust detection of photon-number-splitting (PNS) attacks and concludes with privacy amplification to ensure informationtheoretic security. Experimental validation using a high-fidelity Qiskit simulation with a realistic depolarizing channel model demonstrates a significant improvement in key rate efficiency. In a simulated environment with 15% eavesdropper intervention, our method achieved a 7.8% higher key rate than standard BB84, while successfully maintaining the Quantum Bit Error Rate (QBER) below the 11% security threshold. This work establishes a more robust and efficient framework for practical QKD implementations.
In next-generation networks, including the sixth generation (6G), a large number of computing devices can communicate with ultra-low latency. By implication, 6G capabilities present a massive benefit for the Internet of Things (IoT), considering a wide range of application domains. However, some security concerns in the IoT involving authentication and encryption protocols are currently under investigation. Thus, mechanisms implementing quantum communications in IoT devices have been explored to offer improved security. Algorithmic solutions that enable better quantum key distribution (QKD) selection for authentication and encryption have been developed, but having limited performance considering time requirements. Therefore, a new approach for selecting the best QKD protocol based on a Deep Convolutional Neural Network model, called Tree-CNN, is proposed using the Tanh Exponential Activation Function (TanhExp) that enables IoT devices to handle more secure quantum communications using the 6G network infrastructure. The proposed model is developed, and its performance is compared with classical Convolutional Neural Networks (CNN) and other machine learning methods. The results obtained are superior to the related works, with an Area Under the Curve (AUC) of 99.89% during testing and a time-cost performance of 0.65 s for predicting the best QKD protocol. In addition, we tested our proposal using different transmission distances and three QKD protocols to demonstrate that the prediction and actual results reached similar values. Hence, our proposed model obtained a fast, reliable, and precise solution to solve the challenges of performance and time consumption in selecting the best QKD protocol.