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

arXiv:1906.03779 · New Journal of Physics

Multi-label learning for improving discretely-modulated continuous-variable quantum key distribution

Qin Liao, Gang Xiao, Hai Zhong, Ying Guo

Published Jul 31, 2020• 48 citations
arXivHTMLPDF

Abstract

Abstract We propose a novel scheme for discretely-modulated continuous-variable quantum key distribution (CVQKD) using machine learning technologies, which called multi-label learning-based CVQKD (ML-CVQKD). In particular, the proposed scheme divides the whole quantum system into state learning process and state prediction process. The former is used for training and estimating classifier, and the latter is used for generating final secret key. Meanwhile, a multi-label classification algorithm (MLCA) is also designed as an embedded classifier for distinguishing coherent state. Feature extraction for coherent state and related machine learning-based metrics for the quantum classifier are successively suggested. Security analysis based on the linear bosonic channel assumption shows that MLCA-embedded ML-CVQKD outperforms other existing discretely-modulated CVQKD protocols, such as four-state protocol and eight-state protocol, as well as the original Gaussian-modulated CVQKD protocol, and it will be further enhanced with the increase of modulation variance.

DOI
10.1088/1367-2630/abab3c

Related papers

Machine-learning-based detection for quantum hacking attacks on continuous-variable quantum-key-distribution systems

Chao Ding, Shi Wang, Yaonan Wang +3 more

Continuous-variable quantum key distribution (CVQKD) is a mature technology that can theoretically provide an unconditional security guarantee. However, a practical CVQKD system may be vulnerable to various quantum hacking attacks due to imperfect devices and insufficient assumptions. In this paper, we propose a universal defense strategy called a machine-learning-based attack detection scheme (MADS). Leveraging the combined advantages of density-based spatial clustering of applications with noise (DBSCAN) and multiclass support vector machines (MCSVMs), MADS demonstrates remarkable effectiveness in detecting quantum hacking attacks. Specifically, we first establish a set of attack-related features to extract feature vectors. These vectors are then utilized as input data for DBSCAN to identify and remove any noise or outliers. Finally, the trained MCSVMs are employed to classify and predict the processed data. The predicted results can immediately determine whether or not to generate a final secret key. Simulation results show that the proposed MADS can efficiently detect most quantum hacking attacks and revise the overestimated secret key rates caused by a CVQKD system without any defense strategy to obtain a tighter security bound.

Physical Review A•Jun 28, 2023•14 citations

Discrete-Modulated Coherent-State Quantum Key Distribution with Basis-Encoding

Mingxuan Guo, Peng Huang, Le Huang +4 more

Discrete-modulated coherent-state continuous-variable quantum key distribution (DMCS-CVQKD) is of great value for its simple implementation. However, the traditional DMCS-CVQKD scheme cannot tolerate the high channel excess noise and channel loss, compared to the Gaussian-modulated scheme, and its error correction is still difficult. In this paper, we propose a discrete-modulated coherent-state basis-encoding quantum key distribution (DMCS-BE-QKD) protocol, where the secret keys are encoded in the random choice of 2 measurement bases, i.e., the conjugate quadratures X and P of discrete-modulated coherent states, and it only needs simple binary sequence error correction. We analyze the secret key rate of DMCS-BE-QKD protocol under individual and collective attacks in the linear Gaussian channel. The results show that DMCS-BE-QKD can greatly enhance the ability to tolerate the channel loss and excess noise compared to the original DMCS-CVQKD protocol, which can tolerate approximately 40 dB more channel loss compared to the original DMCS-CVQKD for the realistic value of noise. Finally, a proof-of-principle experiment is conducted under a 50.5-km optical fiber to verify the feasibility of DMCS-BE-QKD. It is based on the consistent physical procedures of the traditional DMCS-CVQKD, which makes it perfectly compatible to deployed terminals and can serve as a multiplier for the practical secure quantum cryptography communication in harsh environments.

Research•Jan 1, 2025•4 citations

Detecting quantum attacks: a machine learning based defense strategy for practical continuous-variable quantum key distribution

Yiyu Mao, Wenti Huang, Hai Zhong +4 more

Abstract The practical security of a continuous-variable quantum key distribution (CVQKD) system is compromised by various attack strategies. The existing countermeasures against these attacks are to exploit different real-time monitoring modules to prevent different types of attacks, which significantly depend on the accuracy of the estimated excess noise and lack a universal defense method. In this paper, we propose a defense strategy for CVQKD systems to address these disadvantages and resist most of the known attack types. We investigate several features of the pulses that would be affected by different types of attacks, derive a feature vector based on these features as the input of an artificial neural network (ANN) model, and show the training and testing process of the ANN model for attack detection and classification. Simulation results show that the proposed scheme can effectively detect most of the known attacks at the cost of reducing a small part of secret keys and transmission distance. It establishes a universal attack detection model by simply monitoring several features of the pulses without knowing the exact type of attack in advance.

New Journal of Physics•Jul 23, 2020•75 citations

Performance Improvement of Discretely Modulated Continuous-Variable Quantum Key Distribution with Untrusted Source via Heralded Hybrid Linear Amplifier

Kunlin Zhou, Xuelin Wu, Yun Jie Mao +3 more

In practical quantum communication networks, the scheme of continuous-variable quantum key distribution (CVQKD) faces a challenge that the entangled source is controlled by a malicious eavesdropper, and although it still can generate a positive key rate and security, its performance needs to be improved, especially in secret key rate and maximum transmission distance. In this paper, we proposed a method based on the four-state discrete modulation and a heralded hybrid linear amplifier to enhance the performance of CVQKD where the entangled source originates from malicious eavesdropper. The four-state CVQKD encodes information by nonorthogonal coherent states in phase space. It has better transmission distance than Gaussian modulation counterpart, especially at low signal-to-noise ratio (SNR). Moreover, the hybrid linear amplifier concatenates a deterministic linear amplifier (DLA) and a noiseless linear amplifier (NLA), which can improve the probability of amplification success and reduce the noise penalty caused by the measurement. Furthermore, the hybrid linear amplifier can raise the SNR of CVQKD and tune between two types of performance for high-gain mode and high noise-reduction mode, therefore it can extend the maximal transmission distance while the entangled source is untrusted.

Entropy•Aug 12, 2020•1 citation

Discretely modulated continuous-variable quantum key distribution with an untrusted entanglement source

Qin Liao, Gang Xiao, Chugui Xu +2 more

The discretely modulated continuous-variable quantum key distribution (DM CVQKD) has been proven to be secure, and a basic assumption for the current theoretical security proof of the DM CVQKD is that the signal source cannot be compromised. However, this assumption is quite unpractical in real quantum communication systems. In this paper, we investigate the DM CVQKD with a special configuration in which the entanglement source is placed at the untrusted channel. With this configuration, the source is no longer protected by the sender but is exposed to the vulnerable environment. In particular, we consider the configuration for two typical DM CVQKD protocols, which are the four-state protocol and the eight-state protocol. Security analysis based on linear bosonic channel shows that the DM CVQKD with an untrusted entanglement source is able to defend itself against the most powerful quantum collective attack in a certain distance range and it can still generate positive secret key rate when considering finite-size effect and composable security, thereby providing a theoretical proof for applying the DM CVQKD system to a realistic environment.

Physical Review A•Sep 8, 2020•56 citations

Discrete-modulated continuous-variable quantum key distribution with a machine-learning-based detector

Jiawei Li, Ying Guo, Xudong Wang +3 more

The discrete-modulated continuous-variable quantum key distribution (DM-CV-QKD) could break the distance limitation of Gaussian-modulated CV-QKD. In practice, the high-performance error correction code plays an important role in DM-CV-QKD and affects the secure transmission distance. However, DM-CV-QKD usually works under low signal-to-noise ratio (SNR) and the design of high-performance error correction code under this condition is difficult, so that it would impose a limitation on further improvement of the secure distance. We propose a DM-CV-QKD with the machine-learning-based detector to further improve the secure distance. The numerical result shows that the proposed scheme could validly improve the system performance. Viewed from another perspective, the proposed scheme could be employed to overcome various impairments induced by the channel and thereby lower the demand of error correction codes on the SNR threshold of the quantum channel without compromising the system performance. The proposed scheme opens the door to applying machine leaning to directly process the raw secret key and improve the performance for CV-QKD systems.

Optical Engineering•Jun 14, 2018•14 citations
Abstract We propose a novel scheme for discretely-modulated continuous-variable quantum key distribution (CVQKD) using machine learning technologies, which called multi-label learning-based CVQKD (ML-CVQKD). In particular, the proposed scheme divides the whole quantum system into state learning process and state prediction process. The former is used for training and estimating classifier, and the latter is used for generating final secret key. Meanwhile, a multi-label classification algorithm (MLCA) is also designed as an embedded classifier for distinguishing coherent state. Feature extraction for coherent state and related machine learning-based metrics for the quantum classifier are successively suggested. Security analysis based on the linear bosonic channel assumption shows that MLCA-embedded ML-CVQKD outperforms other existing discretely-modulated CVQKD protocols, such as four-state protocol and eight-state protocol, as well as the original Gaussian-modulated CVQKD protocol, and it will be further enhanced with the increase of modulation variance.
Continuous-variable quantum key distribution (CVQKD) is a mature technology that can theoretically provide an unconditional security guarantee. However, a practical CVQKD system may be vulnerable to various quantum hacking attacks due to imperfect devices and insufficient assumptions. In this paper, we propose a universal defense strategy called a machine-learning-based attack detection scheme (MADS). Leveraging the combined advantages of density-based spatial clustering of applications with noise (DBSCAN) and multiclass support vector machines (MCSVMs), MADS demonstrates remarkable effectiveness in detecting quantum hacking attacks. Specifically, we first establish a set of attack-related features to extract feature vectors. These vectors are then utilized as input data for DBSCAN to identify and remove any noise or outliers. Finally, the trained MCSVMs are employed to classify and predict the processed data. The predicted results can immediately determine whether or not to generate a final secret key. Simulation results show that the proposed MADS can efficiently detect most quantum hacking attacks and revise the overestimated secret key rates caused by a CVQKD system without any defense strategy to obtain a tighter security bound.
Discrete-modulated coherent-state continuous-variable quantum key distribution (DMCS-CVQKD) is of great value for its simple implementation. However, the traditional DMCS-CVQKD scheme cannot tolerate the high channel excess noise and channel loss, compared to the Gaussian-modulated scheme, and its error correction is still difficult. In this paper, we propose a discrete-modulated coherent-state basis-encoding quantum key distribution (DMCS-BE-QKD) protocol, where the secret keys are encoded in the random choice of 2 measurement bases, i.e., the conjugate quadratures X and P of discrete-modulated coherent states, and it only needs simple binary sequence error correction. We analyze the secret key rate of DMCS-BE-QKD protocol under individual and collective attacks in the linear Gaussian channel. The results show that DMCS-BE-QKD can greatly enhance the ability to tolerate the channel loss and excess noise compared to the original DMCS-CVQKD protocol, which can tolerate approximately 40 dB more channel loss compared to the original DMCS-CVQKD for the realistic value of noise. Finally, a proof-of-principle experiment is conducted under a 50.5-km optical fiber to verify the feasibility of DMCS-BE-QKD. It is based on the consistent physical procedures of the traditional DMCS-CVQKD, which makes it perfectly compatible to deployed terminals and can serve as a multiplier for the practical secure quantum cryptography communication in harsh environments.
Abstract The practical security of a continuous-variable quantum key distribution (CVQKD) system is compromised by various attack strategies. The existing countermeasures against these attacks are to exploit different real-time monitoring modules to prevent different types of attacks, which significantly depend on the accuracy of the estimated excess noise and lack a universal defense method. In this paper, we propose a defense strategy for CVQKD systems to address these disadvantages and resist most of the known attack types. We investigate several features of the pulses that would be affected by different types of attacks, derive a feature vector based on these features as the input of an artificial neural network (ANN) model, and show the training and testing process of the ANN model for attack detection and classification. Simulation results show that the proposed scheme can effectively detect most of the known attacks at the cost of reducing a small part of secret keys and transmission distance. It establishes a universal attack detection model by simply monitoring several features of the pulses without knowing the exact type of attack in advance.
In practical quantum communication networks, the scheme of continuous-variable quantum key distribution (CVQKD) faces a challenge that the entangled source is controlled by a malicious eavesdropper, and although it still can generate a positive key rate and security, its performance needs to be improved, especially in secret key rate and maximum transmission distance. In this paper, we proposed a method based on the four-state discrete modulation and a heralded hybrid linear amplifier to enhance the performance of CVQKD where the entangled source originates from malicious eavesdropper. The four-state CVQKD encodes information by nonorthogonal coherent states in phase space. It has better transmission distance than Gaussian modulation counterpart, especially at low signal-to-noise ratio (SNR). Moreover, the hybrid linear amplifier concatenates a deterministic linear amplifier (DLA) and a noiseless linear amplifier (NLA), which can improve the probability of amplification success and reduce the noise penalty caused by the measurement. Furthermore, the hybrid linear amplifier can raise the SNR of CVQKD and tune between two types of performance for high-gain mode and high noise-reduction mode, therefore it can extend the maximal transmission distance while the entangled source is untrusted.
The discretely modulated continuous-variable quantum key distribution (DM CVQKD) has been proven to be secure, and a basic assumption for the current theoretical security proof of the DM CVQKD is that the signal source cannot be compromised. However, this assumption is quite unpractical in real quantum communication systems. In this paper, we investigate the DM CVQKD with a special configuration in which the entanglement source is placed at the untrusted channel. With this configuration, the source is no longer protected by the sender but is exposed to the vulnerable environment. In particular, we consider the configuration for two typical DM CVQKD protocols, which are the four-state protocol and the eight-state protocol. Security analysis based on linear bosonic channel shows that the DM CVQKD with an untrusted entanglement source is able to defend itself against the most powerful quantum collective attack in a certain distance range and it can still generate positive secret key rate when considering finite-size effect and composable security, thereby providing a theoretical proof for applying the DM CVQKD system to a realistic environment.
The discrete-modulated continuous-variable quantum key distribution (DM-CV-QKD) could break the distance limitation of Gaussian-modulated CV-QKD. In practice, the high-performance error correction code plays an important role in DM-CV-QKD and affects the secure transmission distance. However, DM-CV-QKD usually works under low signal-to-noise ratio (SNR) and the design of high-performance error correction code under this condition is difficult, so that it would impose a limitation on further improvement of the secure distance. We propose a DM-CV-QKD with the machine-learning-based detector to further improve the secure distance. The numerical result shows that the proposed scheme could validly improve the system performance. Viewed from another perspective, the proposed scheme could be employed to overcome various impairments induced by the channel and thereby lower the demand of error correction codes on the SNR threshold of the quantum channel without compromising the system performance. The proposed scheme opens the door to applying machine leaning to directly process the raw secret key and improve the performance for CV-QKD systems.