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
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.
This paper proposes a quantum k-nearest neighbor (QkNN)-based multiclass attack detection framework for CVQKD systems that establishes a direct connection between attack detection and secret key generation, enabling a more realistic security evaluation for practical CVQKD systems.
A dynamic evolutionary attack detection scheme for practical QKD, in which Eve’s attack feature could be vectorized by a well-designed embedding model and dynamically self-update to an attack feature vector database, which significantly improves the generalization capability of quantum attack detection and promotes the practical development of QKD.
Minjie Liu, Ye Chen, Xiaodong Fan et al.· Science China Information Sc...· 0 citations
Quantum Key Distribution (QKD) enjoys information-theoretic security, yet the most damaging attacks against deployed systems exploit the receiver, where the key bit is encoded in which one of a pair of never-identical detectors clicks. The minimal receiver, one rotatable polarizer and one threshold detector, removes that attack surface, and single-detector BB84 demonstrations already run sampled error estimation; the structure of its zero-probability error subensemble, however, has remained uncharacterized. We characterize exactly that structure, introducing a deterministic impossible-event certificate: a click behind a polarizer set orthogonal to the transmitted state has probability exactly zero on an ideal channel, so a single occurrence is a probability-one witness of disturbance; and, since loss deletes clicks and never creates them, the certificate is loss-robust. We prove it sound but incomplete over three polarization states, and show that the four BB84 states close the gap: a fixed-basis intercept-resend attack yields an ideal trip probability of $1/4$ per orthogonal round ($\eta/4$ observed at detection efficiency $\eta$), independent of the interception angle. An illustrative finite-size budget yields 256 retained bits from $\approx 62{,}000$ transmitted rounds at $\eta = 0.1$; under realistic detector noise ($q_0 = 10^{-6}$ per opened gate), each trip retains $\approx 12$ bits of evidence at a sub-percent honest false-abort probability per session. The core ideal trip-probability predictions are numerically verified on the Qiskit circuit simulator, via a released, seed-fixed implementation. Overall, by endowing the minimal-detector receiver of polarization QKD with a conclusive, loss-robust disturbance alarm, our solution lowers the hardware entry cost of security-monitored QKD, hence fostering its adoption at the cost-sensitive network edge.
Twin-field (TF) quantum key distribution (QKD) can overcome the fundamental rate-loss bound of repeaterless QKD, enabling secure communication over long distances. However, in practical implementations, its security relies on accurate intensity modulation, which may be compromised by source imperfections and light-injection attacks. In this work, we investigate the security of the NPP TF-QKD protocol in the presence of imperfect intensity modulation, focusing on Trojan-horse attacks and induced photorefractive attacks. By employing the reference technique, we establish a finite-key security proof that explicitly incorporates this source-side information leakage. Numerical simulations show that with realistic transmitter isolation, the NPP TF-QKD protocol can still surpass the rate-loss bound and achieve secret-key rates close to the ideal case. Our results further demonstrate strong robustness against modulation deviations induced by photorefractive effects. These findings confirm the practical security of TF-QKD under realistic source imperfections and provide quantitative guidance for the design of secure quantum communication systems.
Hua-Jian Ding, Chao Sun, Kai Pan et al.· Optics Express· 0 citations
Federated Learning (FL) enables collaborative model learning without the need to share raw data, but its communication links are vulnerable to interception, replay, and man-in-the-middle (MITM) attacks. The existing key exchange methods rely on computational hardness assumptions, which can be broken by post-quantum attackers. In this paper, a secure federated learning framework improved by Quantum Key Distribution (QKD) is proposed, which integrates BB84-like quantum key generation and authenticated encryption on a per-round basis, as well as Quantum Bit Error Rate (QBER)-assisted intrusion detection. A new cryptographic key is produced in each federated round, making it immune to replay attacks and allowing for detection of tampering. Theoretical calculations show that intercept-resend attacks lead to a minimum expected QBER of 25%, making it easier to detect statistically. Experimental results on the MNIST dataset show near-perfect detection rates for MITM and replay attacks, with QBER values increasing from about 1% (serving as a benign scenario) to about 26% in an attack scenario. Communication overhead is kept below 10%, with negligible computational latency compared to local training. The experiments show that the use of QKD-based key refresh improves FL communication security while still ensuring model convergence.
M. Kumari, Charvi Suri, Isha Suri· 2026 International Conferenc...· 0 citations
Quantum key distribution (QKD) employs quantum states to generate shared cryptographic keys. An attacker interacting with the modeled non-orthogonal quantum signals can affect the monitored statistics, and hence they can be detected under the specified protocol assumptions, but this trait does not inherently authenticate the classical channel, and it does not prevent implementation side channels. In this work, we introduce ModPhase-8 (QUEST), a proposed QKD modulation and adaptive-receiver architecture evaluated through analytical modeling and simulation. Instead of using only a few quantum signal types, our system uses eight carefully designed signal variations created by adjusting the phase between two very short light pulses. The eight phase states are organized into four phase bases, each containing two antipodal states that encode one binary raw-key value. The enlarged signal set diversifies the physical representation of the key bit and changes the state-discrimination problem faced by an eavesdropper, but it does not increase the raw-key payload beyond one bit per successfully sifted signal. On the receiving side, the system adaptively switches between two measurement techniques based on the prevailing channel conditions. This adaptive detection mechanism enhances reliability and helps maintain low error rates even when the communication channel is affected by noise. We provide an analytical security assessment under the stated collective-attack, source, channel, receiver, and trusted-device assumptions, supplemented by attack-specific analyses of intercept–resend, beam-splitting, source-side multi-photon leakage, and selected implementation-related vulnerabilities. Simulation studies were conducted to examine the physical-layer and post-processing behavior of the proposed protocol under explicitly stated channel, receiver, detector, and finite-sample values. Under the adopted simulation model, ModPhase-8 maintains low error rates in the low- and moderate-noise operating regimes and exhibits favorable receiver-level robustness across the investigated channel conditions. The reported rate values are model-based performance estimates rather than rigorously certified secret-key lower bounds. In particular, Qiskit simulation does not establish a composable security proof or an optimal bound on Eve’s information for the exact eight-state time-bin ensemble. A protocol-specific numerical security analysis incorporating the homodyne–heterodyne measurement operators, post-selection, reconciliation efficiency, finite-size effects, and Eve’s Holevo information remains necessary before definitive rate comparisons can be made. ModPhase-8 should therefore be interpreted as a practically motivated receiver and modulation framework whose security-rate performance remains subject to further protocol-specific analysis.
Vidhya Prakash Rajendran, D. Perumalsamy, Basker Palaniswamy et al.· Information· 0 citations