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

Globecom

Deep Reinforcement Learning-Based Joint Security Provisioning in CV-QKD Over Optical Networks

Shifeng Ding, Chun-Kit Chan

Published Dec 8, 2025• 0 citations
Publisher
DOI
10.1109/globecom59602.2025.11432744

Related papers

Deep Reinforcement Learning-Driven Optimization of End-to-End Key Provision in QKD Systems

Yeong-Jun Seok, Ju-Bong Kim, Youn‐Hee Han +3 more

Journal of Network and Systems Management•Feb 6, 2025•6 citations

Quantum-Inspired Deep Reinforcement Learning Framework for Secure, Energy-Efficient Resource Optimization in Next-Generation Quantum Communication Networks

Thanuja R, Dr. Jaswant Kumar Khatik, S. Hemajothi +3 more

International Conference on Networks, Computers and Communications (ICNCCom)•Jul 1, 2026•0 citations

DRL-assisted quantum attack mitigation in resource allocation of CV-QKD over optical networks

Shifeng Ding, Yuansen Cheng, Calvin C. K. Chan

Due to possible imperfect implementation of laser sources and coherent detectors, continuous-variable quantum key distribution (CV-QKD) in optical networks is vulnerable to quantum attacks, which would significantly degrade the secret key rate (SKR) and compromise the security of the quantum keys. The attackers may steal the data encrypted with the compromised keys, leading to service failure and resource wastage. To tackle it, we propose a quantum attack mitigation resource allocation scheme (QAM-RA) for CV-QKD over optical networks. It corrects the biased channel parameters of the compromised quantum channels by conducting appropriate countermeasures, re-analyzes the SKR, and allocates additional quantum resources to compensate for the loss of SKR. A deep reinforcement learning (DRL) framework based on the Asynchronous Advantage Actor-Critic (A3C) algorithm is developed to determine QAM-RA solutions intelligently. Extensive simulations have been conducted to evaluate the performance of the DRL-assisted QAM-RA scheme in two test networks. Simulation results have confirmed the effectiveness of the proposed scheme in mitigating quantum attacks and reducing user request blocking probabilities.

Journal of Optical Communications and Networking•Feb 4, 2025•1 citation

Post-Quantum Secure Network Design using Reinforcement Learning Approaches

M. Tamilarasi, R.K. Soundarayaa, P. Velayutha Perumal +3 more

International Conference on Communication and Electronics Systems (ICCES)•Oct 28, 2025•0 citations

Quantum attack-resistant resource allocation using reinforcement learning in CV-QKD over optical networks

Shifeng Ding, Yuansen Cheng, Calvin Chun-Kit Chan

We propose a quantum attack-resistant resource allocation using reinforcement learning in CV-QKD over optical networks. Simulation results show that it can effectively mitigate quantum attacks and reduce the request blocking probability.

Opto-Electronics and Communications Conference (OECC)•Jun 30, 2024•1 citation

Multidimensional reconciliation scheme using deep learning in continuous-variable quantum key distribution

Yan Feng, Jiangliang Jin, Kun Zhang +4 more

Abstract Information reconciliation is a significant stage in continuous-variable quantum key distribution (CV-QKD) systems as it directly affects the performance of the CV-QKD systems including secret key rate and secure transmission distance. This paper proposes a multidimensional reconciliation scheme using deep learning in CV-QKD systems. Firstly, different neural networks are constructed to obtain the norm information. Secondly, a multidimensional reconciliation scheme with deep learning assisted norm information is proposed which no longer needs to transmit the norm information through the authenticated classical public channel. Finally, simulation results and performance analysis show that, compared with the traditional multidimensional reconciliation scheme, the multidimensional reconciliation scheme with deep learning assisted norm information can decrease the communication traffic to a certain extent.

New Journal of Physics•Apr 22, 2025•3 citations
Due to possible imperfect implementation of laser sources and coherent detectors, continuous-variable quantum key distribution (CV-QKD) in optical networks is vulnerable to quantum attacks, which would significantly degrade the secret key rate (SKR) and compromise the security of the quantum keys. The attackers may steal the data encrypted with the compromised keys, leading to service failure and resource wastage. To tackle it, we propose a quantum attack mitigation resource allocation scheme (QAM-RA) for CV-QKD over optical networks. It corrects the biased channel parameters of the compromised quantum channels by conducting appropriate countermeasures, re-analyzes the SKR, and allocates additional quantum resources to compensate for the loss of SKR. A deep reinforcement learning (DRL) framework based on the Asynchronous Advantage Actor-Critic (A3C) algorithm is developed to determine QAM-RA solutions intelligently. Extensive simulations have been conducted to evaluate the performance of the DRL-assisted QAM-RA scheme in two test networks. Simulation results have confirmed the effectiveness of the proposed scheme in mitigating quantum attacks and reducing user request blocking probabilities.
Abstract Information reconciliation is a significant stage in continuous-variable quantum key distribution (CV-QKD) systems as it directly affects the performance of the CV-QKD systems including secret key rate and secure transmission distance. This paper proposes a multidimensional reconciliation scheme using deep learning in CV-QKD systems. Firstly, different neural networks are constructed to obtain the norm information. Secondly, a multidimensional reconciliation scheme with deep learning assisted norm information is proposed which no longer needs to transmit the norm information through the authenticated classical public channel. Finally, simulation results and performance analysis show that, compared with the traditional multidimensional reconciliation scheme, the multidimensional reconciliation scheme with deep learning assisted norm information can decrease the communication traffic to a certain extent.