Abstract Quantum key distribution (QKD) is a pivotal quantum communication technology but faces practical challenges such as transmission loss and measurement device vulnerabilities. Mode-pairing QKD (MP-QKD) addresses these limitations by dynamically pairing single-photon detection events, enabling secure long-distance communication with simplified experimental requirements. However, optimizing key parameters like pulse intensity remains computationally demanding for traditional numerical methods. To overcome this, this paper shows a machine learning framework that combines Particle swarm optimization (PSO) and three neural networks—Backpropagation neural network (BPNN), XGBoost, and Long short-term memory (LSTM)—to predict optimal pulse intensity under varying environmental conditions. Using PSO-generated datasets, the models map channel loss, error rates, transmission distance, and other parameters to pulse intensity. Simulations demonstrate that BPNN achieves 99.87% prediction accuracy (RMSE: 0.0026) with an average runtime of 13 milliseconds per prediction, outperforming XGBoost and LSTM in both speed and precision. This work establishes a scalable solution for real-time parameter optimization in large-scale QKD networks and highlights the transformative role of machine learning in advancing quantum communication technologies.
Abstract Quantum key distribution (QKD) is a pivotal quantum communication technology but faces practical challenges such as transmission loss and measurement device vulnerabilities. Mode-pairing QKD (MP-QKD) addresses these limitations by dynamically pairing single-photon detection events, enabling secure long-distance communication with simplified experimental requirements. However, optimizing key parameters like pulse intensity remains computationally demanding for traditional numerical methods. To overcome this, this paper shows a machine learning framework that combines Particle swarm optimization (PSO) and three neural networks—Backpropagation neural network (BPNN), XGBoost, and Long short-term memory (LSTM)—to predict optimal pulse intensity under varying environmental conditions. Using PSO-generated datasets, the models map channel loss, error rates, transmission distance, and other parameters to pulse intensity. Simulations demonstrate that BPNN achieves 99.87% prediction accuracy (RMSE: 0.0026) with an average runtime of 13 milliseconds per prediction, outperforming XGBoost and LSTM in both speed and precision. This work establishes a scalable solution for real-time parameter optimization in large-scale QKD networks and highlights the transformative role of machine learning in advancing quantum communication technologies.
The mode-pairing quantum key distribution (MP-QKD) achieves high key generation rates and high security over long-distance, low-loss optical fibers through its mode-pairing technique. In practical applications, when considering finite data sets, MP-QKD requires optimization of parameters such as channel optical bit error rate ( e opt ), detector’s dark count( P d ), the total number of signals( N ), and the number of phase slices( M ). However, traditional exhaustive traversal or local search algorithms do not meet the time and resource requirements of real-time communication systems. Combined with machine learning, the quantum key distribution for parameter optimization prediction has become the mainstream approach. XGBoost, a gradient boosting decision tree (GBDT) algorithm, random forest (RF) representing a classic bagging-based ensemble learning method, and back-propagation neural networks (BPNN) are important algorithms in neural networks. This study employs the LightGBM (light gradient boosting machine) algorithm to predict optimized parameters for MP-QKD. The results demonstrate that LightGBM efficiently and accurately predicts optimal parameters, slightly outperforming XGBoost, RF, and BPNN in parameter prediction, and can serve as a reference for future real-time QKD networks.
Abstract As the number of users in quantum key distribution (QKD) networks continues to grow, parameter selection (e.g., probability of X-bases, signal state strength, and decoy state levels) has become increasingly complex. Traditional methods such as local search algorithms (LSA) are commonly employed for parameter optimization but suffer from significant computational overhead, slow execution on low-power platforms, and resultant system delays. These limitations hinder the scalability and real-time requirements of large-scale QKD networks. To address these challenges, this paper proposes an innovative approach that combines Bayesian optimization with XGBoost model to optimize QKD system parameters. The proposed model is evaluated against random forest (RF) and back-propagation neural network (BPNN) models based on three critical metrics: prediction accuracy, model fitting, and training efficiency. Simulation results demonstrate that the proposed model significantly outperforms both RF and BPNN in terms of accuracy and computational efficiency. Notably, while achieving predictive performance comparable to LSA, the proposed method reduces computation time by three orders of magnitude. This research introduces a novel and efficient framework for QKD parameter optimization, providing new insights and directions for enhancing the performance, scalability, and real-time adaptability of QKD systems.
The mode pairing quantum key distribution (MP-QKD) protocol has attracted considerable attention for its capability to ensure high secure key rates over long distances without requiring global phase locking. However, ensuring symmetric channels for the MP-QKD protocol is challenging in practical quantum communication networks. Previous studies on the asymmetric MP-QKD protocol have relied on ideal decoy state assumptions and infinite-key analysis, which are unattainable for real-world deployment. In this paper, we conduct a security analysis of the asymmetric MP-QKD protocol with the finite-key analysis, where we discard the previously impractical assumptions made in the decoy state method. Combined with statistical fluctuation analysis, we globally optimized the 10 independent parameters in the asymmetric MP-QKD protocol by employing our modified particle swarm optimization. Through further analysis, the simulation results demonstrate that our work achieves improved secure key rates and transmission distances compared to the strategy with additional attenuation. We further investigate the relationship between the intensities and probabilities of signal, decoy, and vacuum states with transmission distance, facilitating their more efficient deployment in future quantum networks.
Abstract Quantum Key Distribution (QKD) is a cornerstone of next-generation cryptographic technologies, offering unparalleled security by utilizing the principles of quantum mechanics. However, practical implementations of QKD face significant challenges, including inefficiencies in key generation, susceptibility to noise, and vulnerabilities to eavesdropping. This work addresses these challenges by proposing a machine learning (ML)-driven approach to optimize QKD protocols, focusing on enhancing both efficiency and security. In this work it is intended to evaluate three advanced protocols Adaptive, Entanglement-Based, and Hybrid under varying conditions such as key length, noise levels, and channel stability. The ML models will include ensemble learning models namely Random Forest and XGBoost, the models will analyze the impact of key parameters on protocol performance and predict efficiency with high accuracy. The results reveal that the Adaptive protocol significantly outperforms the Entanglement-Based and Hybrid protocols, achieving an efficiency of up to 0.80 for a key length of 2500 bits, compared to 0.24 for the Entanglement-Based protocol and 0.26 for the Hybrid protocol. The Adaptive protocol also demonstrates superior detection probability (ranging from 0.84 to 0.85) and a higher probability of detecting eavesdropping (ranging from 0.43 to 0.45). Furthermore, correlation analysis shows a strong positive relationship (r = 0.9985) between key length and efficiency for the Adaptive protocol, highlighting its scalability. In contrast, the Entanglement-Based protocol shows consistent but lower performance across all metrics, while the Hybrid protocol offers a compromise but remains less efficient than the Adaptive protocol. By integrating ML with quantum cryptography, this work bridges the gap between theoretical advancements and practical implementations, providing a scalable framework for optimizing QKD systems in real-world applications. The findings underscore the importance of protocol design and optimization in achieving secure and efficient quantum communication, paving the way for the quantum internet of the future.
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.
Abstract The four‐intensity protocol for measurement‐device‐independent (MDI) quantum key distribution (QKD) is renowned for its excellent performance and extensive experimental implementation. To enhance this protocol, a machine learning‐driven rapid parameter optimization method is developed. This initial step involved a speed‐up technique that quickly pinpoints the worst‐case scenarios with minimal data points during the optimization phase. This is followed by a detailed scan in the key rate calculation phase, streamlining data collection to fit machine learning timelines effectively. Several machine learning models are assessed—Generalized Linear Models (GLM), k‐Nearest Neighbors (KNN), Decision Trees (DT), Random Forests (RF), XGBoost (XGB), and Multilayer Perceptron (MLP)—with a focus on predictive accuracy, efficiency, and robustness. RF and MLP were particularly noteworthy for their superior accuracy and robustness, respectively. This optimized approach significantly speeds up computation, enabling complex calculations to be performed in microseconds on standard personal computers, while still achieving high key rates with limited data. Such advancements are crucial for deploying QKD under dynamic conditions, such as in fluctuating fiber‐optic networks and satellite communications.