Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

QNN-QRL: Quantum Neural Network Integrated with Quantum Reinforcement Learning for Quantum Key Distribution

Bikash K. Behera, Saif Al-Kuwari, Ahmed Farouk

TL;DR

This work targets practical improvements in quantum key distribution by merging quantum machine learning techniques—QRL and QNN—into established QKD protocols. It introduces two QRL-based key-generation schemes (QRL-V.1, QRL-V.2) and four QNN-augmented variants (QNN-BB84, QNN-B92, QNN-QRL-V.1, QNN-QRL-V.2), then evaluates them under six noise channels using metrics such as accuracy, precision, recall, F1 score, ROC, and QBER. The results show that QNN-enhanced protocols, especially QNN-BB84 and the QNN-QRL variants, achieve near-perfect classification performance and the lowest QBER, demonstrating strong robustness against noise and potential for practical QKD deployment. The findings suggest that integrating QML into QKD can significantly improve key generation quality and resilience, guiding future work on scalability and broader quantum learning techniques for quantum-secure communications.

Abstract

Quantum key distribution (QKD) has emerged as a critical component of secure communication in the quantum era, ensuring information-theoretic security. Despite its potential, there are issues in optimizing key generation rates, enhancing security, and incorporating QKD into practical implementations. This research introduces a unique framework for incorporating quantum machine learning (QML) algorithms, notably quantum reinforcement learning (QRL) and quantum neural networks (QNN), into QKD protocols to improve key generation performance. Here, we present two novel QRL-based algorithms, QRL-V.1 and QRL-V.2, and propose the standard BB84 and B92 protocols by integrating QNN algorithms to form QNN-BB84 and QNN-B92. Furthermore, we combine QNN with the above QRL-based algorithms to produce QNN-QRL-V.1 and QNN-QRL-V.2. These unique algorithms and established protocols are compared using evaluation metrics such as accuracy, precision, recall, F1 score, confusion matrices, and ROC curves. The results from the QNN-based proposed algorithms show considerable improvements in key generation quality. The existing and proposed models are investigated in the presence of different noisy channels to check their robustness. The proposed integration of QML algorithms into QKD protocols and their noisy analysis create a new paradigm for efficient key generation, which advances the practical implementation of QKD systems.

QNN-QRL: Quantum Neural Network Integrated with Quantum Reinforcement Learning for Quantum Key Distribution

TL;DR

This work targets practical improvements in quantum key distribution by merging quantum machine learning techniques—QRL and QNN—into established QKD protocols. It introduces two QRL-based key-generation schemes (QRL-V.1, QRL-V.2) and four QNN-augmented variants (QNN-BB84, QNN-B92, QNN-QRL-V.1, QNN-QRL-V.2), then evaluates them under six noise channels using metrics such as accuracy, precision, recall, F1 score, ROC, and QBER. The results show that QNN-enhanced protocols, especially QNN-BB84 and the QNN-QRL variants, achieve near-perfect classification performance and the lowest QBER, demonstrating strong robustness against noise and potential for practical QKD deployment. The findings suggest that integrating QML into QKD can significantly improve key generation quality and resilience, guiding future work on scalability and broader quantum learning techniques for quantum-secure communications.

Abstract

Quantum key distribution (QKD) has emerged as a critical component of secure communication in the quantum era, ensuring information-theoretic security. Despite its potential, there are issues in optimizing key generation rates, enhancing security, and incorporating QKD into practical implementations. This research introduces a unique framework for incorporating quantum machine learning (QML) algorithms, notably quantum reinforcement learning (QRL) and quantum neural networks (QNN), into QKD protocols to improve key generation performance. Here, we present two novel QRL-based algorithms, QRL-V.1 and QRL-V.2, and propose the standard BB84 and B92 protocols by integrating QNN algorithms to form QNN-BB84 and QNN-B92. Furthermore, we combine QNN with the above QRL-based algorithms to produce QNN-QRL-V.1 and QNN-QRL-V.2. These unique algorithms and established protocols are compared using evaluation metrics such as accuracy, precision, recall, F1 score, confusion matrices, and ROC curves. The results from the QNN-based proposed algorithms show considerable improvements in key generation quality. The existing and proposed models are investigated in the presence of different noisy channels to check their robustness. The proposed integration of QML algorithms into QKD protocols and their noisy analysis create a new paradigm for efficient key generation, which advances the practical implementation of QKD systems.

Paper Structure

This paper contains 24 sections, 19 equations, 12 figures, 1 table, 6 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Contribution
  4. Organization
  5. Preliminaries
  6. BB84
  7. B92
  8. QRL
  9. QNN
  10. Proposed Algorithms
  11. QRL Algoirthms
  12. QRL-V.2.
  13. QNN Algorithms
  14. QNN-B92
  15. QNN-QRL Algorithms
  16. ...and 9 more sections

Figures (12)

  • Figure 1: Schematic diagram showing the workings of the proposed QNN-QRL algorithm.
  • Figure 2: A schematic of QRL-V.1. algorithm.
  • Figure 3: (a) Function plots versus angle. $\Delta \theta$ vs. number of iterations for (b) QRL-V.1., and (c) QRL-V.2.
  • Figure 4: Quantum circuits representing (a) QRL-V.1 and (b) QRL-V.2 algorithms.
  • Figure 5: Quantum circuits representing (a) QNN-BB84 and (b) QNN-B92 algorithms.
  • ...and 7 more figures