Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Information

A Survey of Machine Learning Assisted Continuous-Variable Quantum Key Distribution

Nathan K. Long, Robert Malaney, Kenneth J. Grant

Published Oct 10, 2023• 20 citations
Publisher

Abstract

Continuous-variable quantum key distribution (CV-QKD) shows potential for the rapid development of an information-theoretic secure global communication network; however, the complexities of CV-QKD implementation remain a restrictive factor. Machine learning (ML) has recently shown promise in alleviating these complexities. ML has been applied to almost every stage of CV-QKD protocols, including ML-assisted phase error estimation, excess noise estimation, state discrimination, parameter estimation and optimization, key sifting, information reconciliation, and key rate estimation. This survey provides a comprehensive analysis of the current literature on ML-assisted CV-QKD. In addition, the survey compares the ML algorithms assisting CV-QKD with the traditional algorithms they aim to augment, as well as providing recommendations for future directions for ML-assisted CV-QKD research.

DOI
10.3390/info14100553

Related papers

A Survey on Continuous Variable Quantum Key Distribution for Secure Data Transmission: Toward the Future of Secured Quantum-Networks

Mobin Motaharifar, Mahmood Hasani, Hassan Kaatuzian

Abstract Quantum key distribution (QKD) represents a cornerstone of secure communication in the quantum era. While discrete-variable QKD (DV-QKD) protocols were historically the first to demonstrate secure key exchange, continuous-variable QKD (CV-QKD) has emerged as a more practical alternative due to its seamless compatibility with current telecommunications infrastructure. CV-QKD relies on coherent and squeezed states of light, offering significant advantages for integration into modern optical networks. This review comprehensively explores the theoretical underpinnings, technological advancements, and practical challenges of CV-QKD. Special attention is given to the role of photonic integrated circuits (PICs) in enabling scalable and efficient implementation of CV-QKD systems. Furthermore, recent advances in machine learning have been leveraged to optimize CV-QKD performance, with data-driven techniques enhancing noise estimation, parameter optimization, and system security. Additionally, tensor networks provide efficient computational tools for analyzing complex quantum correlations, improving the efficiency and robustness of quantum key distribution protocols. These developments, combined with ongoing improvements in quantum photonic integration, pave the way for the practical deployment of large-scale, high-speed quantum-secure networks.

arXiv:2506.21640•Quantum Information and Computation•May 1, 2025•5 citations

A Survey of Continuous Variable Quantum Key Distribution in Quantum Communication

Samuel Leyikun Birhanu, Milad Ghadimi, Yilun Hai +3 more

Continuous Variable Quantum Key Distribution (CV-QKD) is currently experiencing rapid and significant growth. This can be attributed to its capacity to increase resilience to noise and its ease of integration into current optical communication networks. In this article, we review and survey existing work on CV-QKD post-processing techniques, privacy amplification, and key reconciliation. We also classify protocols based on transmission, preparation, and measurement, which allows for a more systematic and organized understanding of protocols, as well as identifying potential vulnerabilities or weaknesses in each component and allowing for targeted improvements to enhance the overall security and efficiency of protocols. Finally, we outline potential research directions and future challenges that require attention to advance the optimization of CV-QKD technology.

IEEE Access•Jan 1, 2025•3 citations

Machine learning for secure key rate in continuous-variable quantum key distribution.

Min-Gang Zhou, Zhiping Liu, Wen‐Bo Liu +6 more

Continuous-variable quantum key distribution (CV-QKD) with discrete modulation has received widespread attentions because of its experimental simplicity, lower-cost implementation and ease to multiplex with classical optical communication. Recently, some inspiring numerical methods have been applied to analyse the security of discrete-modulated CV-QKD against collective attacks, which promises to obtain considerable key rate over one hundred kilometers of fiber distance. However, numerical methods require up to ten minutes to calculate a secure key rate one time using a high-performance personal computer, which means that extracting the real-time secure key rate is impossible for discrete-modulated CV-QKD system. Here, we present a neural network model to quickly predict the secure key rate of homodyne detection discrete-modulated CV-QKD with good accuracy based on experimental parameters and experimental results. With the excess noise of about $0.01$, the speed of our method is improved by about seven orders of magnitude compared to that of the conventional numerical method. Our method can be extended to quickly solve complex security key rate calculation of a variety of other unstructured quantum key distribution protocols.

•Aug 5, 2021•0 citations

Analysis of Machine Learning Techniques for Information Reconciliation in CV-QKD Systems: Challenges in Practical Scenarios

Mauro Q. Nooblath Neto, Nelson Alves Ferreira Neto

"This paper reviews the challenges associated with implementing InformationReconciliation (IR) techniques in Continuous Variable Quantum Key Distribution (CVQKD) systems, focusing on integrating Machine Learning techniques and embeddedtechnologies such as Field-Programmable Gate Arrays (FPGAs). While CV-QKDsystems are compatible with existing telecommunications infrastructure and capableof high key generation rates, they face significant computational challenges in longdistance communication due to large decoding matrices. This study explores machinelearning approaches to reduce computational complexity and improve post-keyprocessing times, aiming to identify challenges and gaps that can guide future researchin enhancing the efficiency of CV-QKD systems."

•Dec 1, 2024•1 citation

An introductory review of the theory of continuous-variable quantum key distribution: Fundamentals, protocols, and security

Maron F Anka, John A. Mora Rodríguez, Douglas F. Pinto +3 more

Continuous-variable quantum key distribution (CV-QKD) has emerged as a promising approach for secure quantum communication, offering advantages such as high key generation rates, compatibility with standard telecommunication infrastructure, and potential for integration on photonic chips. This review provides an accessible introduction to the theory of CV-QKD, aimed at researchers entering this rapidly developing field. We focus on fundamental concepts, key protocols, and security analysis essential for understanding CV-QKD systems, with a special emphasis on prepare-and-measure protocols using coherent states under asymptotic security conditions. We explain their equivalence to entanglement-based protocols and detail the security proof framework against collective attacks, encompassing both Gaussian and discrete modulation schemes. We also briefly address more advanced topics, including measurement-device-independent CV-QKD and finite-size security analysis. This work is motivated by Brazil's growing investment in quantum communication technologies. By presenting a clear learning path from basic concepts to advanced topics, this work aims to equip newcomers with the essential tools to engage with current research in CV-QKD, thereby supporting the training of a new generation of researchers in this strategic field.

quant-pharXiv:2512.01758•Brazilian Journal of Physics•Dec 2, 2025•4 citations

Key-sifting algorithms for continuous-variable quantum key distribution

Di Jin, Ying Guo, Yijun Wang +2 more

We propose key-sifting algorithms for a continuous-variable quantum key distribution (CV-QKD) protocol using a machine-learning framework based on the isolation forest and a traditional digital signal-processing scheme based on the Wiener filter. In previous works, the key-sifting procedure performs by discarding bits on different measurement basis, but a few useless portions are still retained, so that the transmission distance of CV-QKD systems is limited by excess noise. Here, we develop sifting schemes based on anomaly detection, which provide better feasibility in noisy environments. We compare the detection results for both approaches and estimate the excess noise to confirm the utility of our proposal in real-life applications. Results obtained over a 100-km fiber link indicate that the key-sifting algorithms can ensure low excess noise. Moreover, some of the techniques we develop are applicable to other QKD protocols.

Physical Review A•Jul 27, 2021•10 citations
Continuous-variable quantum key distribution (CV-QKD) shows potential for the rapid development of an information-theoretic secure global communication network; however, the complexities of CV-QKD implementation remain a restrictive factor. Machine learning (ML) has recently shown promise in alleviating these complexities. ML has been applied to almost every stage of CV-QKD protocols, including ML-assisted phase error estimation, excess noise estimation, state discrimination, parameter estimation and optimization, key sifting, information reconciliation, and key rate estimation. This survey provides a comprehensive analysis of the current literature on ML-assisted CV-QKD. In addition, the survey compares the ML algorithms assisting CV-QKD with the traditional algorithms they aim to augment, as well as providing recommendations for future directions for ML-assisted CV-QKD research.
Abstract Quantum key distribution (QKD) represents a cornerstone of secure communication in the quantum era. While discrete-variable QKD (DV-QKD) protocols were historically the first to demonstrate secure key exchange, continuous-variable QKD (CV-QKD) has emerged as a more practical alternative due to its seamless compatibility with current telecommunications infrastructure. CV-QKD relies on coherent and squeezed states of light, offering significant advantages for integration into modern optical networks. This review comprehensively explores the theoretical underpinnings, technological advancements, and practical challenges of CV-QKD. Special attention is given to the role of photonic integrated circuits (PICs) in enabling scalable and efficient implementation of CV-QKD systems. Furthermore, recent advances in machine learning have been leveraged to optimize CV-QKD performance, with data-driven techniques enhancing noise estimation, parameter optimization, and system security. Additionally, tensor networks provide efficient computational tools for analyzing complex quantum correlations, improving the efficiency and robustness of quantum key distribution protocols. These developments, combined with ongoing improvements in quantum photonic integration, pave the way for the practical deployment of large-scale, high-speed quantum-secure networks.
Continuous Variable Quantum Key Distribution (CV-QKD) is currently experiencing rapid and significant growth. This can be attributed to its capacity to increase resilience to noise and its ease of integration into current optical communication networks. In this article, we review and survey existing work on CV-QKD post-processing techniques, privacy amplification, and key reconciliation. We also classify protocols based on transmission, preparation, and measurement, which allows for a more systematic and organized understanding of protocols, as well as identifying potential vulnerabilities or weaknesses in each component and allowing for targeted improvements to enhance the overall security and efficiency of protocols. Finally, we outline potential research directions and future challenges that require attention to advance the optimization of CV-QKD technology.
Continuous-variable quantum key distribution (CV-QKD) with discrete modulation has received widespread attentions because of its experimental simplicity, lower-cost implementation and ease to multiplex with classical optical communication. Recently, some inspiring numerical methods have been applied to analyse the security of discrete-modulated CV-QKD against collective attacks, which promises to obtain considerable key rate over one hundred kilometers of fiber distance. However, numerical methods require up to ten minutes to calculate a secure key rate one time using a high-performance personal computer, which means that extracting the real-time secure key rate is impossible for discrete-modulated CV-QKD system. Here, we present a neural network model to quickly predict the secure key rate of homodyne detection discrete-modulated CV-QKD with good accuracy based on experimental parameters and experimental results. With the excess noise of about 0.010.010.01, the speed of our method is improved by about seven orders of magnitude compared to that of the conventional numerical method. Our method can be extended to quickly solve complex security key rate calculation of a variety of other unstructured quantum key distribution protocols.
"This paper reviews the challenges associated with implementing InformationReconciliation (IR) techniques in Continuous Variable Quantum Key Distribution (CVQKD) systems, focusing on integrating Machine Learning techniques and embeddedtechnologies such as Field-Programmable Gate Arrays (FPGAs). While CV-QKDsystems are compatible with existing telecommunications infrastructure and capableof high key generation rates, they face significant computational challenges in longdistance communication due to large decoding matrices. This study explores machinelearning approaches to reduce computational complexity and improve post-keyprocessing times, aiming to identify challenges and gaps that can guide future researchin enhancing the efficiency of CV-QKD systems."
Continuous-variable quantum key distribution (CV-QKD) has emerged as a promising approach for secure quantum communication, offering advantages such as high key generation rates, compatibility with standard telecommunication infrastructure, and potential for integration on photonic chips. This review provides an accessible introduction to the theory of CV-QKD, aimed at researchers entering this rapidly developing field. We focus on fundamental concepts, key protocols, and security analysis essential for understanding CV-QKD systems, with a special emphasis on prepare-and-measure protocols using coherent states under asymptotic security conditions. We explain their equivalence to entanglement-based protocols and detail the security proof framework against collective attacks, encompassing both Gaussian and discrete modulation schemes. We also briefly address more advanced topics, including measurement-device-independent CV-QKD and finite-size security analysis. This work is motivated by Brazil's growing investment in quantum communication technologies. By presenting a clear learning path from basic concepts to advanced topics, this work aims to equip newcomers with the essential tools to engage with current research in CV-QKD, thereby supporting the training of a new generation of researchers in this strategic field.
We propose key-sifting algorithms for a continuous-variable quantum key distribution (CV-QKD) protocol using a machine-learning framework based on the isolation forest and a traditional digital signal-processing scheme based on the Wiener filter. In previous works, the key-sifting procedure performs by discarding bits on different measurement basis, but a few useless portions are still retained, so that the transmission distance of CV-QKD systems is limited by excess noise. Here, we develop sifting schemes based on anomaly detection, which provide better feasibility in noisy environments. We compare the detection results for both approaches and estimate the excess noise to confirm the utility of our proposal in real-life applications. Results obtained over a 100-km fiber link indicate that the key-sifting algorithms can ensure low excess noise. Moreover, some of the techniques we develop are applicable to other QKD protocols.