Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Resisting Quantum Key Distribution Attacks Using Quantum Machine Learning

Ali Al-kuwari, Noureldin Mohamed, Saif Al-kuwari, Ahmed Farouk, Bikash K. Behera

TL;DR

This work investigates the potential of quantum machine learning (QML) to detect QKD attacks and proposes a Hybrid Quantum Long Short-Term Memory (QLSTM) model to improve detection performance, by combining quantum-enhanced learning with classical deep learning.

Abstract

The emergence of quantum computing poses significant risks to the security of modern communication networks as it breaks today's public-key cryptographic algorithms. Quantum Key Distribution (QKD) offers a promising solution by harnessing the principles of quantum mechanics to establish secure keys. However, practical QKD implementations remain vulnerable to hardware imperfections and advanced attacks such as Photon Number Splitting and Trojan-Horse attacks. In this work, we investigate the potential of quantum machine learning (QML) to detect QKD attacks. In particular, we propose a Hybrid Quantum Long Short-Term Memory (QLSTM) model to improve detection performance. By combining quantum-enhanced learning with classical deep learning, the model captures temporal patterns in QKD data, improving detection accuracy. To evaluate the proposed model, we introduce a QKD dataset that simulates typical operations along with multiple attack scenarios, including Intercept-and-Resend, Photon-Number Splitting, Trojan-Horse, Detector Blinding, and Combined attacks. The dataset includes Quantum Bit Error Rate (QBER), signal and decoy loss rates, and time-based metrics. Our results demonstrate the promising performance of the quantum machine learning approach compared to classical models. The proposed Hybrid QLSTM achieved an accuracy of 94.7% after 50 training epochs. The evaluation is conducted on a semi-realistic, simulation-generated decoy-state BB84 dataset, and the reported performance should be interpreted as a proof-of-concept rather than a final assessment on field-deployed QKD systems.

Resisting Quantum Key Distribution Attacks Using Quantum Machine Learning

TL;DR

This work investigates the potential of quantum machine learning (QML) to detect QKD attacks and proposes a Hybrid Quantum Long Short-Term Memory (QLSTM) model to improve detection performance, by combining quantum-enhanced learning with classical deep learning.

Abstract

The emergence of quantum computing poses significant risks to the security of modern communication networks as it breaks today's public-key cryptographic algorithms. Quantum Key Distribution (QKD) offers a promising solution by harnessing the principles of quantum mechanics to establish secure keys. However, practical QKD implementations remain vulnerable to hardware imperfections and advanced attacks such as Photon Number Splitting and Trojan-Horse attacks. In this work, we investigate the potential of quantum machine learning (QML) to detect QKD attacks. In particular, we propose a Hybrid Quantum Long Short-Term Memory (QLSTM) model to improve detection performance. By combining quantum-enhanced learning with classical deep learning, the model captures temporal patterns in QKD data, improving detection accuracy. To evaluate the proposed model, we introduce a QKD dataset that simulates typical operations along with multiple attack scenarios, including Intercept-and-Resend, Photon-Number Splitting, Trojan-Horse, Detector Blinding, and Combined attacks. The dataset includes Quantum Bit Error Rate (QBER), signal and decoy loss rates, and time-based metrics. Our results demonstrate the promising performance of the quantum machine learning approach compared to classical models. The proposed Hybrid QLSTM achieved an accuracy of 94.7% after 50 training epochs. The evaluation is conducted on a semi-realistic, simulation-generated decoy-state BB84 dataset, and the reported performance should be interpreted as a proof-of-concept rather than a final assessment on field-deployed QKD systems.

Paper Structure

This paper contains 40 sections, 14 equations, 4 figures, 9 tables, 9 algorithms.

Table of Contents

  1. Introduction
  2. Contributions
  3. Organization
  4. Model
  5. Foundations of LSTM and QLSTM
  6. Model Architecture
  7. QLSTM Layer
  8. Classical LSTM Layer
  9. Input Processing
  10. LSTM Processing
  11. Hidden State Extraction
  12. Fully Connected Layer
  13. Dataset
  14. Threat Model
  15. Simulation Setup
  16. ...and 25 more sections

Figures (4)

  • Figure 1: High Level Diagram of The Proposed Hybrid QLSTM Model
  • Figure 2: (a) QLSTM and (b) LSTM Model Architectures
  • Figure 3: Performance comparison of different models: Hybrid QLSTM, LSTM, CNN, RNN, ANN, and Random Forest: a) Accuracy vs. Epochs, b) Precision vs. Epochs, c) Recall vs. Epochs, d) F1-score vs. Epochs, e) Loss vs. Epochs, and f) Final Accuracy Comparison.
  • Figure 4: Confusion matrices for the evaluated models: (a) CNN, (b) LSTM, (c) Hybrid QLSTM, (d) ANN, (e) RNN, and (f) Random Forest.