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 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.
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 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.
Quantum Key Distribution (QKD) offers theoretically unbreakable security by leveraging quantum mechanics. However, practical implementation is challenged by environmental vulnerabilities, noise, and hardware imperfections. Recently, Machine Learning (ML) has emerged as a powerful tool to address these limitations and enhance the real-world viability of QKD systems. In this survey, we review ML techniques applied to improve QKD security and performance across five applications. First, parameter optimization, covering signal calibration, polarization alignment, phase stabilization, modulation state tuning, and post-processing enhancements to maximize secure key generation and minimize error rates. Second, attack detection, where ML models identify and classify quantum threats such as photon-number-splitting and Trojan-horse attacks. Third, protocol selection, leveraging ML to dynamically choose QKD protocols based on operational conditions. Fourth, key performance prediction of core metrics such as Secret Key Rate (SKR) and Quantum Bit Error Rate (QBER). Finally, quantum network management, optimizing large-scale QKD deployments through intelligent routing, node management, and resource allocation. Performance improvements are evaluated using accuracy, reduced QBER, and increased SKR. While ML shows significant potential for finance, government, and defense applications, challenges remain in scalability, computational demands, and real-world testing. Ongoing work should focus on lightweight, generalizable models and standardized benchmarks for practical ML-enhanced QKD deployment.
The rapid development of quantum computing threatens the traditional cryptographic schemes and suggests that the best alternative solution for ensuring the security of key exchange is Quantum Key Distribution (QKD).Despite the information-theoretic security guarantee, the practical implementations of QKD present vulnerabilities that were derived from hardware flaws and the exploitation of the quantum channel.This thesis is intended to address security vulnerabilities by analyzing and proposing an innovative architecture for the identification and mitigation of quantum attacks, via classification techniques of Quantum Machine Learning and the use of the metrics of Quantitative Risk Analysis.The study begins with the concepts of quantum information, the functionality of basic QKD protocols (BB84, B92, E91) and the mathematical modeling of Implementation-level attacks and side-channel attacks in quantum systems.Subsequently, the operational processes of Quantum Support Vector Machine (QSVM) and the Variational Quantum Classifier (VQC) are analyzed during the training phase.Based on the theoretical background of this study, QML-IDPS architecture is proposed.Threat detection and classification are performed using the QSVM and VQC classifiers, while risk metrics are utilized and fed into a classical Intrusion Prevention System (IPS) to support the final decision-making process for the prevention of quantum threats.The final key validated by the threat assessment mechanisms, is then used for data encryption with a classical cryptographic algorithm, such as AES-256.The proper functionality of QML-IDPS architecture is verified with the mathematical Intercept-Resend Use Case Scenario, which basically proves the successful classification and prevention of system anomalies.In conclusion, it is confirmed that the proposed QML-IDPS architecture demonstrates that Quantum Machine Learning combined with Quantitative Risk Analysis can enhance the security and reliability of QKD infrastructures.
By leveraging the fundamental principles of quantum mechanics, quantum cryptography represents a paradigm shift in secure communication by providing information-theoretic security, where any eavesdropping attempt can be intrinsically detected, and by offering resistance to computational attacks, including those posed by future quantum computers that threaten classical cryptographic schemes. To establish Quantum Key Distribution (QKD) as a significant tool in cybersecurity, this study examines the foundational principles of quantum cryptography, focusing on quantum algorithms, quantum bits, and quantum gates. We examine the fundamental QKD protocols and conduct a comparative study of prominent QKD protocols, including BB84, B92, E91, B92, SARG04, COW, Continuous Variable, Six State, Device Independent, and advanced protocols such as MDI-QKD and Twin-Field QKD, to evaluate key rate, distance, and security parameters. A systematic review of the literature has been conducted on the evolution of QKD protocols and networks, QKD integration with advanced technologies like blockchain, IoT, and machine learning, and the practical deployment of quantum communication is studied in this paper. The integration of AI and ML into QKD systems is investigated to explain future algorithm development and performance improvements. Also the function of QKD in quantum networks and the Internet of Things (IoT) is assessed. This paper further delves into the operation of quantum networks, detailing the roles of quantum relays, routers, repeaters, and Free Space Optics (FSO) in enhancing the efficiency and scalability of QKD. Assessing simulators such as SimulaQron, Qiskit, QuNetSim, and QKDNetSim, offering a perception into experimental implementation and protocol validation, resolves the difficulties in quantum-secured communication systems. At last, some security threats are discussed, including Laser damage, Trojan horse attacks, photon-number splitting, and detector blinding, for mitigation of risk strategies. Overall, this work contributes to the importance of QKD and quantum networks in shaping the future of secure wireless communication.
Quantum Key Distribution (QKD) is increasingly recognized as a robust solution to the vulnerabilities posed by quantum computing to classical encryption systems. This paper presents a comprehensive investigation of the BB84 protocol, the foundational QKD scheme, through simulated quantum communication using IBM’s Qiskit framework. The study models quantum key exchange under both ideal and adversarial conditions, including channel noise and intercept-resend attacks. The Quantum Bit Error Rate (QBER) was measured as a function of noise intensity and eavesdropping, confirming that QBER increases predictably in compromised channels. A threshold of 11% QBER was used to determine the viability of secure key generation. Final key retention rates were analyzed across multiple channel scenarios, revealing BB84’s sensitivity to both photon loss and adversarial interference.\n\nSecurity vulnerabilities such as photon-number-splitting and detector blinding were assessed, and countermeasures including decoy-state protocols and authenticated classical channels were proposed. Four key performance graphs were generated to visualize system behavior under realistic operational conditions. The results support BB84’s theoretical advantage in ensuring information-theoretic security while acknowledging real-world limitations in transmission range and hardware reliability. The paper concludes by addressing future improvements in QKD systems, including satellite-based distribution, quantum repeaters, and device-independent implementations. Through simulation-driven analysis, this study validates BB84 as a practical defense against quantum-enabled attacks and underscores the need for continued development and standardization in post-quantum cryptographic infrastructure.
Quantum Machine Learning (QML) offers a transformative approach to financial forecasting by enhancing predictive accuracy and cybersecurity resilience. This study evaluates QML’s effectiveness using financial market data from Yahoo Finance, comparing Quantum Long Short-Term Memory (QLSTM) to classical LSTM and ARIMA models. Security vulnerabilities were assessed using the IEEE DataPort adversarial attack dataset, while encryption performance was analyzed using Quantum Key Distribution (QKD) data from NIST. Experimental results demonstrate that QLSTM outperforms classical models, achieving lower RMSE (1.82), MAE (1.45), and MSE (3.31), indicating superior forecasting precision. Quantum Support Vector Machines (QSVM) exhibit increased adversarial robustness, limiting accuracy degradation to 11.67% under FGSM attacks and 15.60% under PGD attacks, whereas classical models suffer losses exceeding 24%. QKD provides a substantial security advantage over RSA-4096, achieving a 5.87 bps secure key rate and demonstrating over 100 years of resistance to quantum attacks, reinforcing its role as a next-generation cybersecurity mechanism for financial institutions. Despite these advantages, the adoption of QML in financial forecasting faces challenges related to high computational costs, hardware limitations, and integration complexities. Quantum security frameworks require significant infrastructure investments to ensure scalability and reliability. Financial institutions must prioritize QML investment, integrate quantum security mechanisms, and collaborate with regulatory bodies to establish standardized guidelines for secure financial applications. This study contributes to the growing field of quantum-enhanced financial analytics, highlighting its potential to mitigate cyber threats and improve financial forecasting reliability while addressing existing implementation barriers.
Quantum computing advancements pose a growing threat to conventional cryptographic systems based on com- putational hardness assumptions such as RSA and Elliptic Curve Cryptography. Quantum Key Distribution (QKD) has emerged as a theoretically secure alternative by leveraging the fundamental principles of quantum mechanics to establish shared secret keys between communicating parties. However, practical QKD deployments remain vulnerable to channel noise, hardware imperfections, side-channel attacks, and sophisticated intercept- resend strategies that exploit implementation weaknesses. Tra- ditional QKD security analysis relies on static Quantum Bit Error Rate (QBER) thresholds, which are insufficient for dis- tinguishing malicious eavesdropping from natural environmental disturbances. Recent advancements in artificial intelligence and machine learning have introduced intelligent anomaly detec- tion techniques capable of analyzing complex quantum channel behaviour in real time. This paper presents a comprehensive survey of AI-driven threat detection and response systems for quantum cryptographic networks. Various techniques including Random Forest classifiers, deep learning models, Support Vector Machines, and reinforcement learning-based adaptive response mechanisms are discussed along with their strengths and limita- tions. The paper also highlights major research challenges such as false-positive detection, computational overhead, hardware dependency, and limited integration of automated mitigation strategies. Furthermore, a conceptual multimodal framework combining IBM Qiskit-based BB84 simulation, machine learning- based threat classification, and automated Privacy Amplification is discussed as a promising solution for securing next-generation quantum communication infrastructures.