Quantum Key Distribution (QKD) using the BB84 protocol offers the potential for information-theoretic security based upon the principles of quantum mechanics; however, eavesdropping mechanisms such as intercept-resend attacks and ambient noise sources that degrade quantum channel fidelity may render such systems exploitable. We present a oneclass machine learning approach to detect two categories of threats present within BB84 quantum channels: (i) interceptresend eavesdropping committed by an adversarial actor (Eve), and (ii) six types of channel noise. We have trained three unsupervised anomaly detectors (One-Class Support Vector Machine (OC-SVM), Isolation Forest (iForest), and Extended Isolation Forest (Ex-iForest)) on a dataset consisting of 1000 instances (940 clean and 60 anomalous) and tested each of them on separate test sets of 100 instances. With respect to the detection of adversarial attacks, Ex-iForest outperformed both OC-SVM and iForest; it achieved 95.00% accuracy, precision, recall, and F1-score, and when detecting channel noise, it achieved an overall accuracy, precision, recall, and F1-score of 92.00%. Feature importance analysis confirmed that the Quantum Bit Error Rate (QBER) and the fidelity of polarization measurement were the two most discriminative features for adversarial detection while fluctuations of photon detection counts and timing jitter were the two most informative features for channel noise discrimination. These results suggest that ExiForest is a viable, robust, and efficient solution for real-time anomaly detection systems in BB84-based quantum communication systems.
Quantum Key Distribution (QKD) using the BB84 protocol offers the potential for information-theoretic security based upon the principles of quantum mechanics; however, eavesdropping mechanisms such as intercept-resend attacks and ambient noise sources that degrade quantum channel fidelity may render such systems exploitable. We present a oneclass machine learning approach to detect two categories of threats present within BB84 quantum channels: (i) interceptresend eavesdropping committed by an adversarial actor (Eve), and (ii) six types of channel noise. We have trained three unsupervised anomaly detectors (One-Class Support Vector Machine (OC-SVM), Isolation Forest (iForest), and Extended Isolation Forest (Ex-iForest)) on a dataset consisting of 1000 instances (940 clean and 60 anomalous) and tested each of them on separate test sets of 100 instances. With respect to the detection of adversarial attacks, Ex-iForest outperformed both OC-SVM and iForest; it achieved 95.00% accuracy, precision, recall, and F1-score, and when detecting channel noise, it achieved an overall accuracy, precision, recall, and F1-score of 92.00%. Feature importance analysis confirmed that the Quantum Bit Error Rate (QBER) and the fidelity of polarization measurement were the two most discriminative features for adversarial detection while fluctuations of photon detection counts and timing jitter were the two most informative features for channel noise discrimination. These results suggest that ExiForest is a viable, robust, and efficient solution for real-time anomaly detection systems in BB84-based quantum communication systems.
Conventional BB84 Quantum Key Distribution (QKD) systems rely on a fixed 11% Quantum Bit Error Rate (QBER) threshold to detect eavesdropping. However, stealthy attacks can remain below this threshold while still compromising channel security. This paper proposes a temporal QBER based machine learning framework for detecting and classifying eavesdropping attacks in BB84 QKD systems. Rather than relying on average session level QBER, the framework extracts 63 physics-informed temporal features capturing burst behavior, temporal instability, basis dependent asymmetry, and QBER loss interactions. Random Forest, XGBoost, and Support Vector Machine with a Radial Basis Function kernel (SVM-RBF) classifiers are evaluated on seven eavesdropping attacks and a normal channel scenario under noisy and lossy conditions. Averaged over ten independent runs, XGBoost achieves the best performance with 88.01% (0.47%) accuracy and a macro F1 score of 0.8803, while SVM-RBF performs comparably, confirming the robustness of the proposed features. Evaluated as a binary attack-versus-normal detector for comparison with conventional monitoring, a fixed 11% QBER threshold achieves only 25.82% accuracy with a False Negative Rate (FNR) of 0.8477, whereas the proposed framework reduces the FNR to 0.0198, substantially improving detection of stealthy attacks that evade threshold-based monitoring. SHapley Additive exPlanations based (SHAP) explainability shows that physics-informed temporal and channel derived features are highly discriminative for identifying eavesdropping strategies. These results demonstrate that temporal QBER driven machine learning provides an accurate, explainable, and practical framework for multi attack security monitoring in BB84 QKD systems.
Abstract The rapid expansion of Internet of Things (IoT) infrastructures has heightened their exposure to sophisticated adversaries, including those equipped with quantum capabilities. This work introduces a hybrid framework that integrates post-quantum cryptography (PQC), quantum key distribution (QKD), and quantum machine learning (QML) to deliver quantum-resilient anomaly detection. A novel PQC-IoT dataset is generated using real-time Raspberry Pi sensors, enriched with 30+ features spanning 12 traffic classes (9 attacks, 3 benign), and incorporating PQC-specific metadata such as encryption latency and ciphertext size. Security is enforced through Kyber-512 encryption and a BB84-based QKD channel, while anomaly detection is performed using a quantum support vector machine (qSVM). Experimental results show that qSVM consistently outperforms classical SVM and XGBoost by 4--7% in accuracy, precision, recall, and F1-score, achieving up to 97.6% accuracy with encryption overhead limited to 5--7%. The framework maintains a Quantum Bit Error Rate (QBER) below 11% under noise models, validating its robustness. To the best of our knowledge, this is the first reproducible benchmark that unifies PQC, QKD, and QML into a single pipeline, offering a practical pathway toward quantum-secure IoT anomaly detection.
Quantum Key Distribution (QKD) leverages quantum mechanics to achieve information-theoretic secure key ex-change, resilient to both classical and quantum computational attacks. This paper proposes a novel framework that integrates QKD with machine learning-based intrusion detection in Software-Defined Networks (SDNs). Using BB84 and BB92 protocols, we evaluated resilience under intercept-resend and photon number splitting attacks. Furthermore, Random Forest and XGBoost classifiers were enhanced with QKD-generated keys to secure intrusion detection pipelines. The results show improved accuracy (99.8%) and F1-scores (85.12%) compared to classical IDS approaches, highlighting the novelty of combining QKD with ML-driven cyber defense. The study validates performance against benchmark survey works, emphasizing the role of QKD in advancing future-ready cybersecurity architectures.
Quantum Key Distribution (QKD) provides an innovative approach for secure communication by utilizing the principles of quantum mechanics. Among various QKD protocols, the BB84 protocol remains the most widely studied and implemented due to its simplicity and theoretical security guarantees. However, practical implementations of BB84 are vulnerable to several eavesdropping attacks and channel imperfections. This paper presents a comprehensive study on the detection and analysis of eavesdropping attacks in the BB84 protocol. The work focuses on common attacks such as intercept-resend attack, photon-number splitting attack, Trojan horse attack, and phase-covariant cloning attack. The effect of these attacks on Quantum Bit Error Rate (QBER) is analyzed in detail. Simulation-based observations are discussed to demonstrate how QBER increases under malicious interference. The study further explores statistical methods for detecting eavesdropping and examines practical countermeasures including decoy states, privacy amplification, and error correction techniques. The paper concludes that BB84 remains robust against eavesdropping when proper detection and mitigation mechanisms are employed.
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.
Quantum Key Distribution (QKD) provides information-theoretic security by exploiting the principles of quantum mechanics. Among QKD protocols, the BB84 scheme remains the most widely adopted for both theoretical research and practical implementation. A critical parameter determining the reliability and security of BB84 is the Quantum Bit Error Rate (QBER), which quantifies errors in the sifted key arising from channel noise or potential eavesdropping. This paper presents a systematic review and analysis of QBER within the BB84 protocol, examining its calculation, statistical estimation methods, and role in detecting eavesdropping activity. Simulation results, corroborated by reported experimental observations, reveal a near-linear relationship between eavesdropping intensity and QBER, with values approaching 25% under full intercept-resend attacks. Four confidence interval estimation methods, Wald, Wilson, Clopper-Pearson, and Hoeffding's inequality, are compared for robust QBER analysis in finite-key scenarios. Protocol enhancements, including decoy-state methods, hybrid cryptographic models, and quantum-resistant authentication, are discussed as mechanisms to mitigate errors and strengthen resilience across fiber, free-space, underwater, and satellite QKD systems. Open challenges in distinguishing noise-induced errors from malicious eavesdropping, and the role of adaptive error correction and machine-learning-assisted QBER estimation in future quantum networks, are identified as key directions for further research.