Ali Al-Kuwari, Noureldin Mohamed, Saif Al-Kuwari, Ahmed Farouk, Bikash K. Behera
{"title":"Resisting Quantum Key Distribution Attacks Using Quantum Machine Learning","authors":"Ali Al-Kuwari, Noureldin Mohamed, Saif Al-Kuwari, Ahmed Farouk, Bikash K. Behera","doi":"10.1049/qtc2.70028","DOIUrl":"https://doi.org/10.1049/qtc2.70028","url":null,"abstract":"<p>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 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 introduce a realistic QKD dataset that simulates typical QKD operations, along with seven attack scenarios: Intercept-and-resend, photon-number splitting (PNS), Trojan-Horse attacks on the random number generator (RNG), detector blinding, wavelength-dependent Trojan-Horse and combined attacks. 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 the promising performance of the quantum machine learning approach compared to traditional classical machine learning models, highlighting the potential of hybrid techniques to enhance the security of future quantum communication networks. The proposed hybrid QLSTM model achieved an accuracy of 94.7.0% after 50 training epochs, outperforming classical deep learning models such as LSTM, CNN, ANN, random forest and RNN. However, our evaluation is conducted on a semi-realistic, simulation-generated decoy-state BB84 dataset with simplified models of attacks and device imperfections, so the reported performance should be interpreted as a proof-of-concept rather than a final assessment on field-deployed QKD systems.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"7 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70028","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quantum Machine Learning Applications to Medical Images: A Survey","authors":"Mahua Nandy Pal, Debashis De, Dipankar Hazra","doi":"10.1049/qtc2.70026","DOIUrl":"https://doi.org/10.1049/qtc2.70026","url":null,"abstract":"<p>Classical deep learning achieves high accuracy in image analysis tasks but require large volume of data for generalisation. Medical image datasets are often small and expensive to annotate. Arguably, quantum machine learning (QML) has the following benefits over classical machine learning (ML). (i) Quantum superposition and entanglement allow quantum machines to excel over the computational competence of classical computers. (ii) By parallel processing, QML solves problems faster. (iii) QML produces promising results with limited-size image datasets and limited-parameter circuits. The practical advantages of QML over classical methods are still emerging and not consistent across all application domains. Ongoing research in quantum hardware and algorithms are expected to bridge this gap. In this review, we provide an outline of quantum neural networks, quantum convolution neural networks and various hybrid models characterised by continuous learning. We also explore human brain-inspired quantum neuromorphic computing using quantum spiking neural networks, characterised by learning from discrete neuromorphic spikes. We discuss quantum circuits, used for different medical image applications, from the perspectives of the circuit topology, the numbers of input and measurement qubits and rotation and entanglement gates. Furthermore, we conducted a systematic review of the literature on QML-based medical image applications, datasets and benchmarks, and the analysis of the research gap separately indicating possible improvement opportunities.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"7 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70026","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147299958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yassir Al-Karawi, Raad S. Alhumaima, Hamed Al-Raweshidy
{"title":"Cybersecurity Driven Quantum Digital Twin for Proactive Threat Reversal in Open RAN","authors":"Yassir Al-Karawi, Raad S. Alhumaima, Hamed Al-Raweshidy","doi":"10.1049/qtc2.70027","DOIUrl":"https://doi.org/10.1049/qtc2.70027","url":null,"abstract":"<p>A cybersecurity-driven quantum digital twin (CQDT) is introduced to protect networked control chains against adversarial completely positive trace preserving perturbations. The design maps O-RAN telemetry to amplitude-encoded registers, forms multipartite entanglement through GHZ and one-dimensional cluster states and injects bit flip, phase flip and amplitude damping channels tied to measurable indicators. System integrity is tracked using fidelity <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>F</mi>\u0000 <mi>t</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation> ${F}_{t}$</annotation>\u0000 </semantics></math>, von Neumann entropy <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>S</mi>\u0000 <mi>t</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation> ${S}_{t}$</annotation>\u0000 </semantics></math> and trace distance <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mi>D</mi>\u0000 <mi>t</mi>\u0000 </msub>\u0000 </mrow>\u0000 <annotation> ${D}_{t}$</annotation>\u0000 </semantics></math>. A lightweight REINFORCE policy acts on these observables to preserve entanglement and limit decoherence within tight cycle-time budgets. Qiskit simulations maintain average fidelity above 0.91, entropy near 0.35 and trace distance below 0.18 under composite noise. Attack classification exceeds 87% with a software-loop latency of about 19.1 ms covering state preparation, entanglement, CPTP injection, measurement and policy inference. Compared with classical intrusion detection and thresholding over quantum observables, the framework improves detection while reducing false alarms and exposes quantum-state degradation in real time. The result is a reproducible and scalable basis for learning-based quantum-aware protection in disaggregated radio access networks and related systems.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"7 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70027","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146224391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Quantum Key Distribution Networks Design: Overview and Challenges","authors":"Pankaj Kumar, Neel Kanth Kundu, Binayak Kar","doi":"10.1049/qtc2.70029","DOIUrl":"https://doi.org/10.1049/qtc2.70029","url":null,"abstract":"<p>Quantum cryptography has increasingly attracted interest from both industry and academia for its potential in real-world applications. With advancements in quantum electronics, practical quantum devices are now commercially available and poised for broader adoption. Quantum key distribution (QKD) leverages fundamental principles of quantum mechanics to ensure secure communication, whereas quantum key distribution networks (QKDN) serve as the foundational infrastructure for deploying and scaling these secure systems. This paper examines the design methodologies specific to QKD within QKDN, emphasising both the conceptual framework and the practical challenges inherent in the field. In the pursuit of developing robust QKDN design, several key obstacles, related to the foundational QKD technology, must be addressed. These include decoherence, which affects the stability of quantum states and reduces key generation rates; latency, which disrupts synchronisation throughout the QKD network; and intrinsic quantum noise, an inherent property of quantum systems that primarily limits the overall performance of the QKD network. In addition, the limited communication ranges and the requirement for highly specialised hardware complicate the practical deployment of these networks. This work serves as an introductory guide for researchers entering the field, providing an overview of the fundamental principles of QKD network design and the distinctive routing characteristics inherent to such systems. It outlines the essential steps and considerations for building efficient and resilient QKDN infrastructures, including a discussion of the foundational principles, protocols and existing challenges.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"7 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70029","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146224359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Research on PID Parameter Optimisation for BP Neural Network Based on Improved Quantum Genetic Algorithm","authors":"Jianyong Zhan, Xingrong Zhu, Ying Zhou","doi":"10.1049/qtc2.70024","DOIUrl":"10.1049/qtc2.70024","url":null,"abstract":"<p>With the continuous development of industrial intelligent technology, traditional PID algorithms have certain limitations in effectively controlling nonlinear or complex control systems. Therefore, new intelligent PID algorithms are gradually replacing traditional PID algorithms, enabling automatic parameter optimisation. However, these intelligent algorithms face challenges such as getting stuck in local optima and suboptimal convergence effects in certain complex control systems. To address these issues, this paper proposes an improved quantum genetic algorithm that encodes individuals as quantum states and applies quantum operations to update the population, obtaining classical solutions and utilising quantum crossover and quantum mutation to evolve and improve the solutions. This study conducted simulation experiments on a second-order oscillatory process using traditional PID, BP neural network (BPNN) PID, genetic algorithm (GA) BP- NN_PID and the proposed improved quantum genetic algorithm (QGA) BPNN_PID controllers, and recorded the corresponding output responses. The experimental results showed that the QGA enhanced BPNN_PID controller outperforms others, with rise time 2.8 s, overshoot 2.7% and settling time 9.4 s. Additionally, the improved controller exhibits reduced oscillation in the output and demonstrates good control performance for systems that require fast and stable output.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"6 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70024","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145572553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Daniel Sanchez Rosales, Roderick D. Cochran, Samantha D. Isaac, Paul G. Kwiat, Daniel J. Gauthier
{"title":"A Quantum Key Distribution System for Mobile Platforms With Highly Indistinguishable States","authors":"Daniel Sanchez Rosales, Roderick D. Cochran, Samantha D. Isaac, Paul G. Kwiat, Daniel J. Gauthier","doi":"10.1049/qtc2.70025","DOIUrl":"10.1049/qtc2.70025","url":null,"abstract":"<p>Quantum key distribution (QKD) allows two users to exchange a provably secure key for cryptographic applications. In prepare-and-measure QKD protocols, the states must be indistinguishable to prevent information leakage to an eavesdropper performing a side-channel attack. Here, we measure the indistinguishability of quantum states in a prepare-and-measure three-state BB84 polarisation-based decoy state protocol using resonant-cavity light-emitting diodes (RC-LEDs) as the source in the transmitter. We make the spatial, spectral and temporal DOF of the generated quantum states nearly indistinguishable using a spatial filter single-mode fibre, a narrow-band spectral filter and adjustable timing of the electrical pulses driving the RC-LEDs, respectively. The sources have fully indistinguishable transverse spatial modes. The measured fractional mutual information between an assumed eavesdropper and the legitimate receiver is <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>2.39</mn>\u0000 <mo>×</mo>\u0000 <mn>1</mn>\u0000 <msup>\u0000 <mn>0</mn>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>5</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation> $2.39times 1{0}^{-5}$</annotation>\u0000 </semantics></math> due to the spectral distinguishability and <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>4.31</mn>\u0000 <mo>×</mo>\u0000 <mn>1</mn>\u0000 <msup>\u0000 <mn>0</mn>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>5</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation> $4.31times 1{0}^{-5}$</annotation>\u0000 </semantics></math> for the temporal distinguishability. The source is integrated into a full QKD system operating in a laboratory environment, where we achieve a secure key rate of 41.5 kbits/s with an average quantum bit error rate of 2.9%. The low system size, weight and power make it suitable for mobile platforms such as uncrewed aerial vehicles (drones) or automobiles.</p>","PeriodicalId":100651,"journal":{"name":"IET Quantum Communication","volume":"6 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/qtc2.70025","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145572094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}