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

International Conference on Transparent Optical Networks

Machine Learning-Based Polarization Drift Compensation for High Speed DV-QKD Homodyne Receiver

Mariana F. Ramos, Elias Gutmann, Hannes Hübel

Published Jul 2, 2023• 0 citations
Publisher

Abstract

Discrete variables quantum key distribution (DV-QKD), with its well-studied and scrutinized BB84 protocol, benefits from being very attractive for highly secure communications. However, current detection schemes rely on the use of InGaAs SPDAs, which limits not only its use in high temperature environments, but also high secure communication rates. A possible approach is the use of coherent homodyne detection schemes for polarization encoding based DV-QKD combined. To deploy polarization encoding DV-QKD over standard optical fiber high speed networks, the polarization drift suffered due to birefringence over the channel must be compensated. In this work, we use a machine learning (ML) polarization tracking and compensation algorithm combined with a coherent homodyne receiver, thus allowing the deployment of high-speed polarization encoding based DV-QKD in standard optical fibers. The ML-algorithm predicts the SOP evolution keeping the error rate below 1 %. In this way, the overhead to polarization monitoring is reduced leading to a secure key exchange rate (SKR) of 79 Mbps for a communication over 40 km optical fiber.

DOI
10.1109/icton59386.2023.10207380

Related papers

ML-Aided SOP Compensation to Increase Key Exchange Rate in QKD Systems

Morteza Ahmadian, Marc Ruiz, Jaume Comellas +1 more

Secure communications have become a requirement for virtually all kind of applications. Currently, two distant parties can generate shared random secret keys by using public key cryptography. However, quantum computing represents one of the greatest threats for the finite complexity of the mathematics behind public key cryptography. In contrast, Quantum Key Distribution (QKD) relies on properties of quantum mechanics, which enables eavesdropping detection and guarantees the security of the key. Among QKD systems, polarization encoded QKD has been successfully tested in laboratory experiments and recently demonstrated in closed environments. In this paper, we propose a Machine Learning (ML) -based polarization tracking and compensation that is able to keep shared secret key exchange to high rates even under large fiber stressing events. Exhaustive results using both synthetic and experimental data show remarkable performance, which can simplify the design of both quantum transmitter and receiver, as well as enable the use of aerial optical cables, thus reducing total QKD system cost.

International Conference on Transparent Optical Networks•Jul 2, 2023•3 citations

Polarization based discrete variables quantum key distribution via conjugated homodyne detection

Mariana F. Ramos, Armando N. Pinto, Nuno A. Silva

Optical homodyne detection is widely adopted in continuous-variable quantum key distribution for high-rate field measurement quadratures. Besides that, those detection schemes have been being implemented for single-photon statistics characterization in the field of quantum tomography. In this work, we propose a discrete-variable quantum key distribution (DV-QKD) implementation that combines the use of phase modulators for high-speed state of polarization (SOP) generation, with a conjugate homodyne detection scheme which enables the deployment of high speed QKD systems. The channel discretization relies on the application of a detection threshold that allows to map the measured voltages as a click or no-click. Our scheme relies also on the use of a time-multiplexed pilot tone-quantum signal architecture which enables the use of a Bob locally generated local oscillator and opens the door to an effective polarization drift compensation scheme. Besides that, our results shows that for higher detection threshold values we obtain a very low quantum bit error rate (QBER) on the sifted key. Nevertheless, due to huge number of discarded qubits the obtained secure key length abruptly decreases. From our results, we observe that optimizing the detection threshold and considering a system operating at 500 MHz symbol generation clock, a secure key rate of approximately 46.9 Mbps, with a sifted QBER of [Formula: see text] over 40 km of optical fiber. This considering the error correction and privacy amplification steps necessary to obtain a final secure key.

Scientific Reports•Apr 12, 2022•16 citations

Cost-Effective ML-Powered Polarization-Encoded Quantum Key Distribution

Morteza Ahmadian, Marc Ruiz, Jaume Comellas +1 more

Secure communications have become a requirement for virtually all kind of applications. Currently, two distant parties can generate shared random secret keys by using public key cryptography. However, quantum computing represents one of the greatest threats for the finite complexity of the mathematics behind public key cryptography. In contrast, Quantum Key Distribution (QKD) relies on properties of quantum mechanics, which enables eavesdropping detection and guarantees the security of the key. Among QKD systems, polarization encoded QKD has been successfully tested in laboratory experiments and recently demonstrated in closed environments. The main drawback of QKD is its high cost, which comes, among others, from:i) the requirements for the quantum transmitters and receivers; andii) the need of carefully selecting the fibers supporting the quantum channel to minimize the environmental effects that could dramatically change the polarization state of photons. In this paper, we propose a Machine Learning (ML) -based polarization tracking and compensation that is able to keep shared secret key exchange to high rates even under large fiber stressing events. Exhaustive results using both synthetic and experimental data show remarkable performance, which can simplify the design of both quantum transmitter and receiver, as well as enable the use of aerial optical cables, thus reducing total QKD system cost.

Journal of Lightwave Technology•Mar 8, 2022•18 citations

Efficient Compensation Methods for SOP Drift in Hybrid Fiber-FSO Link-Based QKD Systems

Nelson Jesus Muga, Sara T. Mantey, Hugo Costa +2 more

Quantum key distribution (QKD) uses fundamental principles of quantum mechanics to enable information-theoretic secure communication, emerging as a key element for future-proof secure communication infrastructures. This contrasts with classical cryptographic systems, whose security relies on computational assumptions and is therefore vulnerable to advances in algorithms and computing power. From a practical perspective, QKD systems greatly benefit from the use of already deployed fiber-optic networks, which facilitate scalable and cost-effective implementation. However, optical fibers are inherently affected by intrinsic and extrinsic birefringence, leading to random and timevarying changes in the state of polarization (SOP) of the transmitted qubits. These polarization fluctuations can severely degrade system performance, making effective SOP tracking and compensation techniques essential. This paper presents our recent investigations on SOP drift compensation in fiber-link-based QKD systems, comparing different approaches with the aim of identifying solutions that combine simplicity, robustness, and high efficiency. Additionally, we discuss applying these algorithms in the context of beyond fiber-optic quantum channels, specifically free-space optical (FSO) links and hybrid links combining fiber and free-space segments.

International Conference on Transparent Optical Networks•Jul 1, 2026•0 citations

Robustness of continuous variable quantum key distribution under strong polarization drift

Margarida Almeida, Armando N. Pinto, Nuno A. Silva

Abstract The practical deployment of Continuous Variables Quantum Key Distribution (CV-QKD) systems benefits from existing optical fiber telecommunication infrastructures. However, optical fibers introduce random variations in the state of polarization, which degrades the system’s performance. We consider a CV-QKD system featuring a polarization diversity heterodyne receiver and the constant modulus algorithm (CMA) to compensate for the polarization drifts in the quantum channel. Our setup can effectively realign Alice’s quantum signal with Bob’s local oscillator for polarization drift variances below 10 −10 . This value is compatible with most experimental implementations, allowing for accurate estimation of the channel transmission and excess noise parameters. Our results establish operational limits for passive polarization drift compensation using a polarization diversity receiver combined with digital CMA, validating its use to compensate for the polarization drift in real-world implementations approximating the ideal scenario of no polarization drift, for polarization drift variances below 10 −10 . This enables long-term stability in CV-QKD systems, eliminating the need for active polarization controllers and manual adjustments.

EPJ Quantum Technology•Oct 15, 2025•1 citation

Quantifying the effect of polarization drift on continuous-variable QKD security

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

Continuous-Variable (CV)-Quantum Key Distribution (QKD) addresses the key distribution problem encoding the information using coherent states, ensuring security by monitoring the noise of the exchanged states. This approach offers high key rates and compatibility with standard telecommunication infrastructure, with fiber-deployed CV-QKD systems extensively demonstrated. However, the long-term stability of these systems remains challenged by the polarization drift. While polarization effects are often assumed negligible or actively compensated, their impact on the secret key rate (SKR) over extended operation has not been fully quantified. In this work, we present a comprehensive analysis of the temporal evolution of the Stokes parameters and SKR under varying polarization drift variances, adopting a stochastic approach to emulate the polarization drift. Through extensive simulations, we identify three distinct regimes: an ideal-case approximation with negligible effects; a transition region with progressive signal distortion, biased channel parameter estimation, and SKR degradation; and a worst-case scenario leading to angular displacements near 90°, collapsed correlation, and null SKR. The polarization coherence time rapidly decreases with increasing polarization drift variance, from nearly one hour at 10−14 to sub-second durations above 10−11. These findings offer critical insights into the interplay between polarization dynamics and system security, informing the design of robust CV-QKD deployments. While active compensation of polarization drift using dynamic controllers require continuous monitoring, passive strategies such as polarization-diversity receivers and digital signal processing-based techniques provide practical alternatives for field-deployed CV-QKD systems.

SPIE Quantum Technologies•May 28, 2026•0 citations
Discrete variables quantum key distribution (DV-QKD), with its well-studied and scrutinized BB84 protocol, benefits from being very attractive for highly secure communications. However, current detection schemes rely on the use of InGaAs SPDAs, which limits not only its use in high temperature environments, but also high secure communication rates. A possible approach is the use of coherent homodyne detection schemes for polarization encoding based DV-QKD combined. To deploy polarization encoding DV-QKD over standard optical fiber high speed networks, the polarization drift suffered due to birefringence over the channel must be compensated. In this work, we use a machine learning (ML) polarization tracking and compensation algorithm combined with a coherent homodyne receiver, thus allowing the deployment of high-speed polarization encoding based DV-QKD in standard optical fibers. The ML-algorithm predicts the SOP evolution keeping the error rate below 1 %. In this way, the overhead to polarization monitoring is reduced leading to a secure key exchange rate (SKR) of 79 Mbps for a communication over 40 km optical fiber.
Secure communications have become a requirement for virtually all kind of applications. Currently, two distant parties can generate shared random secret keys by using public key cryptography. However, quantum computing represents one of the greatest threats for the finite complexity of the mathematics behind public key cryptography. In contrast, Quantum Key Distribution (QKD) relies on properties of quantum mechanics, which enables eavesdropping detection and guarantees the security of the key. Among QKD systems, polarization encoded QKD has been successfully tested in laboratory experiments and recently demonstrated in closed environments. In this paper, we propose a Machine Learning (ML) -based polarization tracking and compensation that is able to keep shared secret key exchange to high rates even under large fiber stressing events. Exhaustive results using both synthetic and experimental data show remarkable performance, which can simplify the design of both quantum transmitter and receiver, as well as enable the use of aerial optical cables, thus reducing total QKD system cost.
Optical homodyne detection is widely adopted in continuous-variable quantum key distribution for high-rate field measurement quadratures. Besides that, those detection schemes have been being implemented for single-photon statistics characterization in the field of quantum tomography. In this work, we propose a discrete-variable quantum key distribution (DV-QKD) implementation that combines the use of phase modulators for high-speed state of polarization (SOP) generation, with a conjugate homodyne detection scheme which enables the deployment of high speed QKD systems. The channel discretization relies on the application of a detection threshold that allows to map the measured voltages as a click or no-click. Our scheme relies also on the use of a time-multiplexed pilot tone-quantum signal architecture which enables the use of a Bob locally generated local oscillator and opens the door to an effective polarization drift compensation scheme. Besides that, our results shows that for higher detection threshold values we obtain a very low quantum bit error rate (QBER) on the sifted key. Nevertheless, due to huge number of discarded qubits the obtained secure key length abruptly decreases. From our results, we observe that optimizing the detection threshold and considering a system operating at 500 MHz symbol generation clock, a secure key rate of approximately 46.9 Mbps, with a sifted QBER of [Formula: see text] over 40 km of optical fiber. This considering the error correction and privacy amplification steps necessary to obtain a final secure key.
Secure communications have become a requirement for virtually all kind of applications. Currently, two distant parties can generate shared random secret keys by using public key cryptography. However, quantum computing represents one of the greatest threats for the finite complexity of the mathematics behind public key cryptography. In contrast, Quantum Key Distribution (QKD) relies on properties of quantum mechanics, which enables eavesdropping detection and guarantees the security of the key. Among QKD systems, polarization encoded QKD has been successfully tested in laboratory experiments and recently demonstrated in closed environments. The main drawback of QKD is its high cost, which comes, among others, from:i) the requirements for the quantum transmitters and receivers; andii) the need of carefully selecting the fibers supporting the quantum channel to minimize the environmental effects that could dramatically change the polarization state of photons. In this paper, we propose a Machine Learning (ML) -based polarization tracking and compensation that is able to keep shared secret key exchange to high rates even under large fiber stressing events. Exhaustive results using both synthetic and experimental data show remarkable performance, which can simplify the design of both quantum transmitter and receiver, as well as enable the use of aerial optical cables, thus reducing total QKD system cost.
Quantum key distribution (QKD) uses fundamental principles of quantum mechanics to enable information-theoretic secure communication, emerging as a key element for future-proof secure communication infrastructures. This contrasts with classical cryptographic systems, whose security relies on computational assumptions and is therefore vulnerable to advances in algorithms and computing power. From a practical perspective, QKD systems greatly benefit from the use of already deployed fiber-optic networks, which facilitate scalable and cost-effective implementation. However, optical fibers are inherently affected by intrinsic and extrinsic birefringence, leading to random and timevarying changes in the state of polarization (SOP) of the transmitted qubits. These polarization fluctuations can severely degrade system performance, making effective SOP tracking and compensation techniques essential. This paper presents our recent investigations on SOP drift compensation in fiber-link-based QKD systems, comparing different approaches with the aim of identifying solutions that combine simplicity, robustness, and high efficiency. Additionally, we discuss applying these algorithms in the context of beyond fiber-optic quantum channels, specifically free-space optical (FSO) links and hybrid links combining fiber and free-space segments.
Abstract The practical deployment of Continuous Variables Quantum Key Distribution (CV-QKD) systems benefits from existing optical fiber telecommunication infrastructures. However, optical fibers introduce random variations in the state of polarization, which degrades the system’s performance. We consider a CV-QKD system featuring a polarization diversity heterodyne receiver and the constant modulus algorithm (CMA) to compensate for the polarization drifts in the quantum channel. Our setup can effectively realign Alice’s quantum signal with Bob’s local oscillator for polarization drift variances below 10 −10 . This value is compatible with most experimental implementations, allowing for accurate estimation of the channel transmission and excess noise parameters. Our results establish operational limits for passive polarization drift compensation using a polarization diversity receiver combined with digital CMA, validating its use to compensate for the polarization drift in real-world implementations approximating the ideal scenario of no polarization drift, for polarization drift variances below 10 −10 . This enables long-term stability in CV-QKD systems, eliminating the need for active polarization controllers and manual adjustments.
Continuous-Variable (CV)-Quantum Key Distribution (QKD) addresses the key distribution problem encoding the information using coherent states, ensuring security by monitoring the noise of the exchanged states. This approach offers high key rates and compatibility with standard telecommunication infrastructure, with fiber-deployed CV-QKD systems extensively demonstrated. However, the long-term stability of these systems remains challenged by the polarization drift. While polarization effects are often assumed negligible or actively compensated, their impact on the secret key rate (SKR) over extended operation has not been fully quantified. In this work, we present a comprehensive analysis of the temporal evolution of the Stokes parameters and SKR under varying polarization drift variances, adopting a stochastic approach to emulate the polarization drift. Through extensive simulations, we identify three distinct regimes: an ideal-case approximation with negligible effects; a transition region with progressive signal distortion, biased channel parameter estimation, and SKR degradation; and a worst-case scenario leading to angular displacements near 90°, collapsed correlation, and null SKR. The polarization coherence time rapidly decreases with increasing polarization drift variance, from nearly one hour at 10−14 to sub-second durations above 10−11. These findings offer critical insights into the interplay between polarization dynamics and system security, informing the design of robust CV-QKD deployments. While active compensation of polarization drift using dynamic controllers require continuous monitoring, passive strategies such as polarization-diversity receivers and digital signal processing-based techniques provide practical alternatives for field-deployed CV-QKD systems.