Resisting Quantum Key Distribution Attacks Using Quantum Machine Learning

Abstract

The emergence of quantum computing poses significant risks to the security of mod- ern communication networks as it breaks today’s public-key cryptographic algorithms. Quantum Key Distribution (QKD) offers a promising solution by harnessing the prin- ciples of quantum mechanics to establish secure keys. However, practical QKD imple- mentations remain vulnerable to hardware imperfections and advanced attacks such as Photon Number Splitting and Trojan-Horse attacks. In this thesis, we investigate the potential of using quantum machine learning (QML) to detect popular QKD attacks. In particular, we propose a Hybrid Quantum Long Short-Term Memory (QLSTM) model to improve the detection of common QKD attacks. By combining quantum-enhanced learning with classical deep learning, the model captures complex temporal patterns in QKD data, improving detection accuracy. To evaluate the proposed model, we intro- duce a realistic QKD dataset simulating normal QKD operations along with three attack scenarios, Intercept-and-Resend, Photon-Number Splitting (PNS), and Trojan-Horse at- tacks. The dataset includes quantum security metrics such as Quantum Bit Error Rate (QBER), measurement entropy, signal and decoy loss rates, and time-based metrics, ensuring an accurate representation of real-world conditions. Our results demonstrate promising performance of the quantum machine learning approach compared to tra- ditional classical machine learning models, highlighting the potential of hybrid tech- niques to enhance the security of future quantum communication networks. The pro- posed Hybrid QLSTM model achieved an accuracy of 99.0% after 100 training epochs, outperforming classical deep learning models such as LSTM, CNN, and QCNN. Addi- tionally, when evaluated in a binary classification setting by converting all attack labels to one label, the model showed slight enhancement achieving 99.1% accuracy, further demonstrating its effectiveness in QKD intrusion detection.

Date of Award	2025
Original language	American English
Awarding Institution	HBKU College of Science and Engineering