ABSTRACT Hybrid quantum networks will be the communication backbone of the future quantum internet, linking together heterogeneous discrete‐variable (DV) and continuous‐variable (CV) quantum systems. However, current quantum key distribution protocols assume a static basis and are not designed for dynamically changing hybrid quantum environments. This paper suggests an adaptive machine learning‐assisted teleportation quantum key distribution framework that integrates the following steps into a quantum‐classical architecture: hybrid DV–CV communication, quantum teleportation, adaptive basis selection and neural‐assisted quantum error correction. Optimal measurement basis prediction, by means of a supervised multilayer perceptron (MLP), using six real‐time channel descriptors, allows for intelligent protocol adaptation under heterogeneous channel conditions. The framework proposed was realized in Qiskit Aer and Scikit‐learn and tested with 6000 different realisations of the different channels. The classification accuracy was 99.44% while the average inference latency was only 0.0011 ms per channel sample, making it possible to use the adaptive basis selector in real time. The teleportation fidelity of AMT‐QKD was 0.899 at a representative channel noise level of 10%, with a quantum bit error rate (QBER) of 0.088, a secret key rate of 0.404 and an eavesdropper mutual information of only . They are shown to be more robust, have less information leakage, and be more secure in generating keys under realistic channel impairments when compared to other protocols, including BB84, Enhanced BB84, B92, BBM92, E91 and CV‐QKD. The findings provide a robust framework for the deployment of AMT‐QKD in secure communication in future hybrid quantum networks and quantum internet applications.
ABSTRACT Hybrid quantum networks will be the communication backbone of the future quantum internet, linking together heterogeneous discrete‐variable (DV) and continuous‐variable (CV) quantum systems. However, current quantum key distribution protocols assume a static basis and are not designed for dynamically changing hybrid quantum environments. This paper suggests an adaptive machine learning‐assisted teleportation quantum key distribution framework that integrates the following steps into a quantum‐classical architecture: hybrid DV–CV communication, quantum teleportation, adaptive basis selection and neural‐assisted quantum error correction. Optimal measurement basis prediction, by means of a supervised multilayer perceptron (MLP), using six real‐time channel descriptors, allows for intelligent protocol adaptation under heterogeneous channel conditions. The framework proposed was realized in Qiskit Aer and Scikit‐learn and tested with 6000 different realisations of the different channels. The classification accuracy was 99.44% while the average inference latency was only 0.0011 ms per channel sample, making it possible to use the adaptive basis selector in real time. The teleportation fidelity of AMT‐QKD was 0.899 at a representative channel noise level of 10%, with a quantum bit error rate (QBER) of 0.088, a secret key rate of 0.404 and an eavesdropper mutual information of only . They are shown to be more robust, have less information leakage, and be more secure in generating keys under realistic channel impairments when compared to other protocols, including BB84, Enhanced BB84, B92, BBM92, E91 and CV‐QKD. The findings provide a robust framework for the deployment of AMT‐QKD in secure communication in future hybrid quantum networks and quantum internet applications.
ABSTRACT The rapid evolution of quantum computing poses a significant threat to classical cryptographic systems like Rivest‐Shamir‐Adleman (RSA) and Elliptic Curve Cryptography (ECC), which rely on the computational hardness of problems such as integer factorization and discrete logarithms. Quantum algorithms such as Shor's algorithm can solve these problems quickly, which undermines the foundations on which classical cryptography relies. Quantum Key Distribution (QKD) is an alternative to the classical methods, which promises information‐theoretic security based on quantum mechanics. Currently, there are existing QKD protocols, including BB84, B92, E91, and GHZ, all of which exhibit various real‐world limitations. For example, these QKD protocols can be vulnerable to a variety of side‐channel attacks (e.g., detector blinding, photon‐number‐splitting) and neglect to consider fluctuating network conditions. Current QKD protocols also fail to accommodate scalability for many‐to‐many or noise‐limited scenarios. Many implementations of the existing QKD protocols and other common forms of networks remain static, relying on arbitrary decisions of fixed values that yield simple linear conclusions that can be predicted and targeted in the real‐world environment. To address these omissions, we propose a new framework for dynamic or adaptive hybrid QKD in which we incorporate BB84, B92, E91, and GHZ into one common approach with all protocols selected based on a probability‐weighted distribution of (0.3, 0.2, 0.3, 0.2). In the hybrid QKD implementation, the probability weights of protocol selection are assigned with partiality toward BB84, E91, B92, and GHZ, respectively. This may also introduce a higher variety of protocols and diversity in approaches that will further limit cross‐protocol possibilities of attack vectors, while increasing the possible flexibility of adaptability in attacked situations. In addition, we incorporate an artificial intelligence (AI)‐based optimization module using a neural network to evaluate local environmental noise and quantum bit error rate (QBER) in real time. It adjusts protocol selection probabilities dynamically based on both historical and live operational data to optimize throughput while maintaining low error rates. The system architecture supports modular and parallel operation and has been mapped out and designed to be scalable and compatible with future quantum networks. We test our system using IBM's Qiskit AerSimulator utilizing a 14‐qubit register with 100 rounds of a 1% depolarization noise model, which significantly outperformed static hybrids such as Chen et al. in terms of both key rate and QBER. Our system consistently produced an average QBER of 0.02 and a key generation rate of 12 bits per round. E91 consistently produced CHSH violating confirming the fidelity of the entanglement, while BB84 displayed no QBER on all rounds. This work demonstrates the first fully integrated, AI‐assisted, dynamic hybrid QKD system. It includes all advantageous features of a QKD protocol: the dynamic adaptability of the protocol allows for a performance driven environment, the use of entangled states provides increased security, and a bottom‐up approach to real‐time optimization creating a robust, scalable, and agnostic system to any hardware used by post‐quantum cryptographic infrastructures.
Quantum communication networks represent the foundation for next-generation ultra-secure information transfer. However, practical deployment is limited by noise, decoherence, and the lack of adaptive mechanisms for protocol selection and traffic monitoring. Existing studies confirm the potential of machine learning in Quantum Key Distribution (QKD) and anomaly detection, but most approaches remain static and struggle to scale under dynamic conditions. In this paper, we present a hybrid machine learning-quantum framework designed to enhance adaptability and performance in quantum networks. First, we propose a reinforcement learning-enhanced Tree-CNN for QKD protocol selection, achieving an AUC of 99.95% with reduced decision latency of 0.42 s compared to the baseline Tree-CNN (99.89%, 0.65 s). Second, for anomaly detection, we design a hybrid Quantum Autoencoder (QAE) integrated with a Variational Autoencoder (VAE) and Quantum Kernel SVM, which improves detection accuracy to 98% and F1-score to 98%, outperforming prior QAE-based approaches (92%/90%). Finally, an ML-assisted repeater optimization strategy demonstrates up to 20% higher secure key rates at 200 km. Together, these contributions establish an adaptive, scalable, and 6G-ready solution toward realizing a practical quantum internet.
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.
Quantum Key Distribution (QKD) has turned out to be a promising approach to secure communication systems. Twin-field QKD (TF-QKD) is one of the protocols that allow long-range secure communication to be provided beyond the traditional rate-distance constraints. Nevertheless, the instability of the phases, noises in the channels, and fixed mechanisms to control the system pose challenges to implementing large-scale TF-QKD networks in practice. The present paper suggests an AI-assisted adaptive framework of TF-QKD networks to enhance the performance of robustness, scalability, and communication. The proposed solution incorporates a predictive model which is based on machine learning to estimate phase drift, optimize correction parameters in real time. The hybrid quantum-classical architecture is designed in which an intelligent control layer is continuous to monitor channel conditions and optimize system adaptability. Simulation outcomes have shown that proposed framework can reduce Quantum Bit Error Rate (QBER) of the system by about 20-30% and increase the rate of secure key generation and overall system performance when compared to traditional methods of these systems where the system is controlled by a static system. A better scalability and stability of the proposed system to different channel conditions is also observed. These findings indicate the possibilities of incorporating artificial intelligence into the future intelligent quantum communication networks.
Despite the robust security guarantees of Quantum Key Distribution (QKD), practical deployment is hindered by dynamic channel noise and complex parameter optimization. We propose AML-QKD, a protocol-agnostic machine learning framework designed to maximize the Secure Key Rate (SKR) and minimize the Quantum Bit Error Rate (QBER) across the BB84, E91, and COW protocols. AML-QKD integrates Temporal Convolutional Networks (TCNs) for short-horizon forecasting of channel fluctuations, using a Proximal Policy Optimization (PPO) agent for real-time parameter tuning, while strictly adhering to composable security constraints. Simulations under realistic depolarizing and amplitude-damping noise demonstrate a 14-25% increase in median SKR and a reduction in median QBER from 3.0% to 1.5%. Furthermore, an exploratory Quantum Reinforcement Learning (QRL) extension reveals a distinct quantum advantage for entanglement-based protocols (E91), achieving a 29.2% throughput gain by natively processing non-local correlations. Our findings suggest that AML-QKD can offer a potentially resilient, security-preserving control architecture for next-generation quantum networks.
Abstract Quantum key distribution (QKD) systems represent a cornerstone of secure quantum communication, relying on post-processing procedures to generate shared keys. Among these, error correction (EC) is a critical and computationally demanding step, where the estimation of the quantum bit error rate (QBER) plays a pivotal role in optimizing code rates for LDPC-based protocols. Traditional QBER estimation methods, grounded in physical models and statistics, often struggle with real-world variability and outliers, leading to suboptimal performance. In this study, we propose a novel machine learning framework for QBER forecasting, reframing the problem as a time-series prediction task. Leveraging real-world data from quantum transmitters, we evaluated a suite of models, including gradient boosting with autoregressive components, exponential smoothing hybrids, and deep neural networks, to predict QBER with greater precision. Through extensive experiments, our approach demonstrates significant improvements in error correction efficiency compared to traditional methods, particularly under challenging conditions like system calibration drifts and non-stationary signal behavior. The results highlight the potential of lightweight and interpretable machine learning models, such as gradient-boosted exponential smoothing, to outperform complex neural architectures in real-world scenarios. This research contributes to the advancement of quantum cryptography by enabling faster and more robust key generation, with reduced information disclosure during reconciliation. Our findings open new avenues for integrating machine learning into QKD systems for adaptive and scalable quantum communication.