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 Mobile Internet, Cloud Computing and Information Security (MICCIS)

Predictive Phase Drift Tracking in Practical Quantum Key Distribution Via LSTM Algorithms

Lijun Zhang, Dongsheng He

Published Apr 11, 2025• 0 citations
Publisher

Abstract

Quantum Key Distribution (QKD) systems face challenges due to quantum state drift caused by environmental variations. This paper introduces a phase drift compensation algorithm for QKD systems based on Long Short Term Memory (LSTM) networks. This algorithm only learns, predicts, and compensates for phase drift from intermediate data generated during QKD transmission, without the need for additional data acquisition modules such as environmental monitoring. The experimental results show that the algorithm has high accuracy in tracking phase drift. It performs well on the test set and can accurately match actual scanned data. When implemented in practical GHz QKD systems, this algorithm can increase transmission efficiency by 15 % without reducing the bit error rate. In addition, as the algorithm does not rely on environmental monitoring equipment or high-intensity emission light conditions, it enhances the security of the system and reduces potential security risks.

DOI
10.1109/miccis66057.2025.00076

Related papers

Automatic phase compensation of a continuous-variable quantum-key-distribution system via deep learning

Zhe-Kun Zhang, Weiqi Liu, Jin Qi +2 more

In a practical continuous-variable quantum-key-distribution (CVQKD) system, it is vital to accurately evaluate and then compensate for the phase drifts of the signals, so that the involved system can achieve better performance and stability. In this paper, based on the long short-term memory network (LSTM) model, an automatic phase compensation approach of the CVQKD system is proposed. The LSTM model is first trained to predict the phase drift value of the quantum signal relative to the local oscillator over time. Then, the predicted phase drift value can be used by Alice to reconstruct her data. Finally, Alice and Bob can obtain the raw key, so that the CVQKD system can achieve enhancements in terms of performance and stability. The experimental results indicate that the proposed LSTM-based automatic phase compensation algorithm can accurately predict the phase drift value and perform phase compensation instead of real-time phase drift measurement, which improves the performance of the CVQKD system without requiring any additional quantum resources and extra experimental hardware.

Physical Review A•Jun 30, 2023•10 citations

Real-time compensation of phase drift for phase-encoded quantum key distribution systems

Lijun Zhang, Yonggang Wang, Zhen−Qiang Yin +7 more

Phase drift is an inherent problem in phase-encoded quantum key distribution (QKD) systems. The current active phase tracking and compensation solutions cannot satisfy the requirements of a system with nonlinearity in phase modulation. This paper presents a four-phase scanning method, which is based on the quantitative analysis of the quantum bit error rate (QBER) from phase drift and the performance requirements of phase compensation. By obtaining the four interference fringes and adjusting the coding matrix of the system, this method automatically calculates the accurate driving voltages for the phase modulator. The implementation and experimental tests show that the proposed method can compensate phase drift caused by environmental changes and the system’s nonlinearity, and is applicable to large-scale QKD networks.

Chinese Science Bulletin•Jul 11, 2011•21 citations

Real-Time Phase Tracking Scheme With Mismatched-Basis Data for Phase-Coding Quantum Key Distribution

Dong Wang, Xiaotian Song, Liangjiang Zhou +1 more

Phase drift is an inevitable problem in the practical implementation of phase-coding quantum key distribution (QKD) systems. Conventional active phase tracking and compensation solutions cannot be implemented during the key transmission process, resulting in reduced efficiency of the system. In this paper, we propose a single-photon level real-time phase tracking scheme using only the estimated quantum bit error rate (QBER) and mismatched-basis data to acquire the phase drift parameter instead of a phase scanning process or reference light pulses, without extra hardware or interrupting the transmission of quantum signals. This scheme is applied into a phase-coding QKD system with active phase disturbance and obtains an average QBER of $1.01\%$ with a standard derivation of $0.37\%$ over 50 h of continuous operation. Experimental results show that this scheme enables QKD systems to operate continuously with long-term stability and keep a low level of QBER even with rapid phase drift, suggesting its suitability for practical applications.

IEEE photonics journal•Apr 13, 2020•9 citations

Machine Learning-Assisted Measurement Device-Independent Quantum Key Distribution on Reference Frame Calibration

Sihao Zhang, Jing-Yang Liu, Guigen Zeng +3 more

In most of the realistic measurement device-independent quantum key distribution (MDI-QKD) systems, efficient, real-time feedback controls are required to maintain system stability when facing disturbance from either external environment or imperfect internal components. Traditionally, people either use a "scanning-and-transmitting" program or insert an extra device to make a phase reference frame calibration for a stable high-visibility interference, resulting in higher system complexity and lower transmission efficiency. In this work, we build a machine learning-assisted MDI-QKD system, where a machine learning model-the long short-term memory (LSTM) network-is for the first time to apply onto the MDI-QKD system for reference frame calibrations. In this machine learning-assisted MDI-QKD system, one can predict out the phase drift between the two users in advance, and actively perform real-time phase compensations, dramatically increasing the key transmission efficiency. Furthermore, we carry out corresponding experimental demonstration over 100 km and 250 km commercial standard single-mode fibers, verifying the effectiveness of the approach.

Entropy•Sep 24, 2021•8 citations

Efficient carrier-recovery method for simple self-referenced continuous-variable quantum key distribution with a long-short-term memory network

Le Huang, Peng Huang, Shurong Wei +4 more

Local local oscillator (LLO) continuous-variable quantum key distribution (CVQKD) systems have gained prominence due to their security advantages with LO generated locally. However, the nonsynchronization of two lasers leads to phase drift, a detrimental phenomenon that restricts excess noise suppression. Prevailing solutions, such as pilot-multiplexing schemes, offer better recovery results than pilot-sequential schemes, but at the expense of increased system complexity and demanding technical requirements. In this work, we introduce an innovative carrier-recovery strategy employing the long-short-term memory (LSTM) neural network, aiming to optimize the recovery performance in the simple self-referenced CVQKD systems with the pilot-sequential scheme. Through temporal modeling, the LSTM network proficiently predicts and compensates for the rapid phase drifts. Experimental validations conducted in both fiber and free-space channels underscore the effectiveness of our method for carrier recovery. In practical CVQKD experiments, our LSTM-based approach yields a near 50% reduction in excess noise, leading to a significant increase in secret key rates when compared with the traditional pilot-sequential method. The simplicity of hardware and operation positions our scheme as a superior alternative for current mainstream pilot-multiplexing CVQKD systems, particularly appealing for on-chip implementation and satellite-to-ground quantum communication applications.

Physical Review Applied•Nov 27, 2024•6 citations

Active phase compensation in phase encoded QKD system based on least square algorithm

Cao Zheng-we

Phase drift is the main source of errors for phase encoding quantum key distribution(QKD) system,and it is an important factor influencing the practical applications of the system.At present,there are some kinds of methods to solve the phase drift problem.They may reduce the phase drift to some extent,but they also have many shortcomings,such as large amount of calculation,low accuracy and complex system.In this paper,we put forward a kind of active phase compensation method based on least squares.Scanning a small number phase points under the condition of a single photon,we can get phase compensation parameters by applying the least square algorithm.The experimental results show that the method gains phase drift parameter in shorter time with less computational cost to complete the realtime active compensation.It can improve the QKD system′s performance and efficiency to a certain extent.

Journal of Optoelectronics·laser•Jan 1, 2014•0 citations
Quantum Key Distribution (QKD) systems face challenges due to quantum state drift caused by environmental variations. This paper introduces a phase drift compensation algorithm for QKD systems based on Long Short Term Memory (LSTM) networks. This algorithm only learns, predicts, and compensates for phase drift from intermediate data generated during QKD transmission, without the need for additional data acquisition modules such as environmental monitoring. The experimental results show that the algorithm has high accuracy in tracking phase drift. It performs well on the test set and can accurately match actual scanned data. When implemented in practical GHz QKD systems, this algorithm can increase transmission efficiency by 15 % without reducing the bit error rate. In addition, as the algorithm does not rely on environmental monitoring equipment or high-intensity emission light conditions, it enhances the security of the system and reduces potential security risks.
In a practical continuous-variable quantum-key-distribution (CVQKD) system, it is vital to accurately evaluate and then compensate for the phase drifts of the signals, so that the involved system can achieve better performance and stability. In this paper, based on the long short-term memory network (LSTM) model, an automatic phase compensation approach of the CVQKD system is proposed. The LSTM model is first trained to predict the phase drift value of the quantum signal relative to the local oscillator over time. Then, the predicted phase drift value can be used by Alice to reconstruct her data. Finally, Alice and Bob can obtain the raw key, so that the CVQKD system can achieve enhancements in terms of performance and stability. The experimental results indicate that the proposed LSTM-based automatic phase compensation algorithm can accurately predict the phase drift value and perform phase compensation instead of real-time phase drift measurement, which improves the performance of the CVQKD system without requiring any additional quantum resources and extra experimental hardware.
Phase drift is an inherent problem in phase-encoded quantum key distribution (QKD) systems. The current active phase tracking and compensation solutions cannot satisfy the requirements of a system with nonlinearity in phase modulation. This paper presents a four-phase scanning method, which is based on the quantitative analysis of the quantum bit error rate (QBER) from phase drift and the performance requirements of phase compensation. By obtaining the four interference fringes and adjusting the coding matrix of the system, this method automatically calculates the accurate driving voltages for the phase modulator. The implementation and experimental tests show that the proposed method can compensate phase drift caused by environmental changes and the system’s nonlinearity, and is applicable to large-scale QKD networks.
Phase drift is an inevitable problem in the practical implementation of phase-coding quantum key distribution (QKD) systems. Conventional active phase tracking and compensation solutions cannot be implemented during the key transmission process, resulting in reduced efficiency of the system. In this paper, we propose a single-photon level real-time phase tracking scheme using only the estimated quantum bit error rate (QBER) and mismatched-basis data to acquire the phase drift parameter instead of a phase scanning process or reference light pulses, without extra hardware or interrupting the transmission of quantum signals. This scheme is applied into a phase-coding QKD system with active phase disturbance and obtains an average QBER of 1.01%1.01\%1.01% with a standard derivation of 0.37%0.37\%0.37% over 50 h of continuous operation. Experimental results show that this scheme enables QKD systems to operate continuously with long-term stability and keep a low level of QBER even with rapid phase drift, suggesting its suitability for practical applications.
In most of the realistic measurement device-independent quantum key distribution (MDI-QKD) systems, efficient, real-time feedback controls are required to maintain system stability when facing disturbance from either external environment or imperfect internal components. Traditionally, people either use a "scanning-and-transmitting" program or insert an extra device to make a phase reference frame calibration for a stable high-visibility interference, resulting in higher system complexity and lower transmission efficiency. In this work, we build a machine learning-assisted MDI-QKD system, where a machine learning model-the long short-term memory (LSTM) network-is for the first time to apply onto the MDI-QKD system for reference frame calibrations. In this machine learning-assisted MDI-QKD system, one can predict out the phase drift between the two users in advance, and actively perform real-time phase compensations, dramatically increasing the key transmission efficiency. Furthermore, we carry out corresponding experimental demonstration over 100 km and 250 km commercial standard single-mode fibers, verifying the effectiveness of the approach.
Local local oscillator (LLO) continuous-variable quantum key distribution (CVQKD) systems have gained prominence due to their security advantages with LO generated locally. However, the nonsynchronization of two lasers leads to phase drift, a detrimental phenomenon that restricts excess noise suppression. Prevailing solutions, such as pilot-multiplexing schemes, offer better recovery results than pilot-sequential schemes, but at the expense of increased system complexity and demanding technical requirements. In this work, we introduce an innovative carrier-recovery strategy employing the long-short-term memory (LSTM) neural network, aiming to optimize the recovery performance in the simple self-referenced CVQKD systems with the pilot-sequential scheme. Through temporal modeling, the LSTM network proficiently predicts and compensates for the rapid phase drifts. Experimental validations conducted in both fiber and free-space channels underscore the effectiveness of our method for carrier recovery. In practical CVQKD experiments, our LSTM-based approach yields a near 50% reduction in excess noise, leading to a significant increase in secret key rates when compared with the traditional pilot-sequential method. The simplicity of hardware and operation positions our scheme as a superior alternative for current mainstream pilot-multiplexing CVQKD systems, particularly appealing for on-chip implementation and satellite-to-ground quantum communication applications.
Phase drift is the main source of errors for phase encoding quantum key distribution(QKD) system,and it is an important factor influencing the practical applications of the system.At present,there are some kinds of methods to solve the phase drift problem.They may reduce the phase drift to some extent,but they also have many shortcomings,such as large amount of calculation,low accuracy and complex system.In this paper,we put forward a kind of active phase compensation method based on least squares.Scanning a small number phase points under the condition of a single photon,we can get phase compensation parameters by applying the least square algorithm.The experimental results show that the method gains phase drift parameter in shorter time with less computational cost to complete the realtime active compensation.It can improve the QKD system′s performance and efficiency to a certain extent.