Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Development and Justification of a Physical Layer Model Based on Monitoring Data for Quantum Key Distribution

Gian-Luca Haiden

TL;DR

The work tackles practical imperfections in QKD by leveraging monitoring data to construct a physical-layer model and compare it against ML-based predictors. It combines a theoretically grounded COW-based SKR model with data-driven neural-network approaches to forecast system performance across multiple links. The results show that ML models achieve superior accuracy and generalization, particularly when incorporating historical SKR and link-loss information, and highlight interpolation as more reliable than extrapolation for cross-link prediction. The study lays the groundwork for long-term SKR forecasting to prevent key exhaustion and to enable proactive management of QKD networks in real-world deployments.

Abstract

Quantum Key Distribution (QKD) is a promising technique for ensuring long-term security in communication systems. Unlike conventional key exchange methods like RSA, which quantum computers could theoretically break [1], QKD offers enhanced security based on quantum mechanics [2]. Despite its maturity and commercial availability, QKD devices often have undisclosed implementations and are tamper-protected. This thesis addresses the practical imperfections of QKD systems, such as low and fluctuating Secret Key Rates (SKR) and unstable performance. By applying theoretical SKR derivations to measurement data from a QKD system in Poland, we gain insights into current system performance and develop machine learning (ML) models to predict system behavior. Our methodologies include creating a theoretical QKD model [2] and implementing ML models using tools like Keras (TensorFlow [3]). Key findings reveal that while theoretical models offer foundational insights, ML models provide superior accuracy in forecasting QKD system performance, adapting to environmental and operational parameters. This thesis highlights the limitations of theoretical models and underscores the practical relevance of ML models for QKD systems. Future research should focus on developing a comprehensive physical layer model capable of doing long-term forcasting of the SKR. Such a model could prevent an encryption system form running out of keys if the SKR drops significantly. In summary, this thesis establishes a foundational approach for using ML models to predict QKD system performance, paving the way for future advancements in SKR long-term predictions.

Development and Justification of a Physical Layer Model Based on Monitoring Data for Quantum Key Distribution

TL;DR

The work tackles practical imperfections in QKD by leveraging monitoring data to construct a physical-layer model and compare it against ML-based predictors. It combines a theoretically grounded COW-based SKR model with data-driven neural-network approaches to forecast system performance across multiple links. The results show that ML models achieve superior accuracy and generalization, particularly when incorporating historical SKR and link-loss information, and highlight interpolation as more reliable than extrapolation for cross-link prediction. The study lays the groundwork for long-term SKR forecasting to prevent key exhaustion and to enable proactive management of QKD networks in real-world deployments.

Abstract

Quantum Key Distribution (QKD) is a promising technique for ensuring long-term security in communication systems. Unlike conventional key exchange methods like RSA, which quantum computers could theoretically break [1], QKD offers enhanced security based on quantum mechanics [2]. Despite its maturity and commercial availability, QKD devices often have undisclosed implementations and are tamper-protected. This thesis addresses the practical imperfections of QKD systems, such as low and fluctuating Secret Key Rates (SKR) and unstable performance. By applying theoretical SKR derivations to measurement data from a QKD system in Poland, we gain insights into current system performance and develop machine learning (ML) models to predict system behavior. Our methodologies include creating a theoretical QKD model [2] and implementing ML models using tools like Keras (TensorFlow [3]). Key findings reveal that while theoretical models offer foundational insights, ML models provide superior accuracy in forecasting QKD system performance, adapting to environmental and operational parameters. This thesis highlights the limitations of theoretical models and underscores the practical relevance of ML models for QKD systems. Future research should focus on developing a comprehensive physical layer model capable of doing long-term forcasting of the SKR. Such a model could prevent an encryption system form running out of keys if the SKR drops significantly. In summary, this thesis establishes a foundational approach for using ML models to predict QKD system performance, paving the way for future advancements in SKR long-term predictions.

Paper Structure

This paper contains 48 sections, 15 equations, 14 figures, 13 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Objectives
  4. Thesis Structure
  5. Background
  6. Technical Background
  7. Network Security
  8. Terms and Definitions
  9. Classical Encryption and its Weaknesses
  10. QKD as a more Secure Solution
  11. State-of-the-art Solutions
  12. Objectives
  13. Methodology
  14. Methodology for Data Collection
  15. Monitoring Equipment and Data Acquisition
  16. ...and 33 more sections

Figures (14)

  • Figure 1: Illustration of the relationship between Alice, Bob and Eve
  • Figure 2: Conceptional setup for BB84
  • Figure 3: Illustraition of COW Protocol
  • Figure 4: Measured SKR of link 1 with respect to time and histogram
  • Figure 5: QKD Network Setup in Poland
  • ...and 9 more figures