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

Optical Fiber Communication Conference

Machine learning based joint polarization and phase compensation for CV-QKD

Hou-Man Chin, Adnan A. E. Hajomer, Nitin Jain, Ulrik L. Andersen, Tobias Gehring

Published Jan 1, 2023• 11 citations
Publisher

Abstract

We investigated a machine learning method for joint estimation of polarization and phase for use in a Gaussian modulated CV-QKD system, over an 18 hour period measured on a installed fiber with 5.5 dB attenuation.
DOI
10.23919/ofc49934.2023.10116174

Related papers

Machine learning based joint polarization and phase compensation for CV-QKD

Hou-Man Chin, Adnan A. E. Hajomer, Nitin Jain +2 more

We investigated a machine learning method for joint estimation of polarization and phase for use in a Gaussian modulated CV-QKD system, over an 18 hour period measured on a installed fiber with 5.5 dB attenuation.

arXiv:2211.06246•Nov 11, 2022•2 citations

Towards optimum phase noise compensation for CV-QKD systems

Hou-Man Chin, Nitin Jain, Ulrik L. Andersen +1 more

We experimentally examine the performance of a machine learning based phase estimation and compensation framework for Gaussian modulated continuous variable quan-tum key distribution relative to a transmitted local oscillator and ideal phase compensation.

Conference on Lasers and Electro-Optics•Jan 1, 2023•1 citation

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

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

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.

Information•Oct 10, 2023•24 citations

Machine learning aided carrier recovery in continuous-variable quantum key distribution

Hou-Man Chin, Nitin Jain, Darko Zibar +2 more

Abstract The secret key rate of a continuous-variable quantum key distribution (CV-QKD) system is limited by excess noise. A key issue typical to all modern CV-QKD systems implemented with a reference or pilot signal and an independent local oscillator is controlling the excess noise generated from the frequency and phase noise accrued by the transmitter and receiver. Therefore accurate phase estimation and compensation, so-called carrier recovery, is a critical subsystem of CV-QKD. Here, we explore the implementation of a machine learning framework based on Bayesian inference, namely an unscented Kalman filter (UKF), for estimation of phase noise and compare it to a standard reference method and a previously demonstrated machine learning method. Experimental results obtained over a 20-km fibre-optic link indicate that the UKF can ensure very low excess noise even at low pilot powers. The measurements exhibited low variance and high stability in excess noise over a wide range of pilot signal to noise ratios. This may enable CV-QKD systems with low hardware implementation complexity which can seamlessly work on diverse transmission lines.

arXiv:2002.09321•npj Quantum Information•Feb 4, 2021•92 citations

Polarization Multiplexing CV-QKD with Polarization Drift Pre-Compensation

Margarida Almeida, Íris Guilherme, Armando N. Pinto +1 more

Practical implementations of Continuous Variable (CV) Quantum Key Distribution (QKD) systems can be performed over the existing optical fiber telecommunication infrastructure. However, optical fibers suffer from random variations in the state of polarization affecting the performance of the system. In this work, we study the impact of the polarization drift on the performance of a CV-QKD setup with a polarization diversity receiver, in which the polarization drift is pre-compensated on Alice’s side. We show that pre-compensating for the polarization drift can successfully realign Alice’s and Bob’s raw signal, without affecting the excess noise, up to a polarization drift variance of 10−10, compatible with most practical implementations.

International Conference on Transparent Optical Networks•Jul 6, 2025•0 citations

Mode Mismatch Mitigation in Gaussian-Modulated CV-QKD

Svitlana Matsenko, Amirhossein Ghazisaeidi, Marcin Jarzyna +4 more

Technical limitations in pulse shaping lead to mode mismatch, which significantly reduces the secure key rate in CV-QKD systems. To address this, a machine learning approach is employed to optimize the transmitter pulse-shape, effectively minimizing mode mismatch and yielding substantial performance improvements. ©2025

arXiv:2505.07726•European Conference on Optical Communication•Sep 28, 2025•1 citation
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 The secret key rate of a continuous-variable quantum key distribution (CV-QKD) system is limited by excess noise. A key issue typical to all modern CV-QKD systems implemented with a reference or pilot signal and an independent local oscillator is controlling the excess noise generated from the frequency and phase noise accrued by the transmitter and receiver. Therefore accurate phase estimation and compensation, so-called carrier recovery, is a critical subsystem of CV-QKD. Here, we explore the implementation of a machine learning framework based on Bayesian inference, namely an unscented Kalman filter (UKF), for estimation of phase noise and compare it to a standard reference method and a previously demonstrated machine learning method. Experimental results obtained over a 20-km fibre-optic link indicate that the UKF can ensure very low excess noise even at low pilot powers. The measurements exhibited low variance and high stability in excess noise over a wide range of pilot signal to noise ratios. This may enable CV-QKD systems with low hardware implementation complexity which can seamlessly work on diverse transmission lines.
Practical implementations of Continuous Variable (CV) Quantum Key Distribution (QKD) systems can be performed over the existing optical fiber telecommunication infrastructure. However, optical fibers suffer from random variations in the state of polarization affecting the performance of the system. In this work, we study the impact of the polarization drift on the performance of a CV-QKD setup with a polarization diversity receiver, in which the polarization drift is pre-compensated on Alice’s side. We show that pre-compensating for the polarization drift can successfully realign Alice’s and Bob’s raw signal, without affecting the excess noise, up to a polarization drift variance of 10−10, compatible with most practical implementations.