Quantum Key Distribution (QKD) techniques provide theoretically invulnerable security for cryptographic key exchange. However, hardware limitations, such as the use of weak coherent photon sources instead of a single-photon source, make it vulnerable to photon-number splitting (PNS) attacks. In a PNS attack Eve selectively intercepts multi-photon pulses while allowing single-photon pulses to pass through. PNS attacks do not affect the quantum bit error rate (QBER), rendering traditional QBER-based monitoring ineffective. Hence, to detect the attack in such cases, it becomes imperative to statistically monitor parameters such as photon counts at the detector, SKR, and shifted key length to identify the attack. In this paper, we propose two complementary deep learning-based frameworks for detection of the PNS attack in the QKD setup. The first operates directly on the raw photon sequence recorded at the receiver, and is realised as a 1-D convolutional network as well as a deeper residual 1-D CNN. The second operates on a compact 13-dimensional feature vector derived from photon statistics, secure-key length, and protocol scalars, and is realised as both a baseline feed-forward network and a deeper residual ANN with skip connections. Together, these four models let us study attack detection across two distinct input modalities. We further establish where each model is best suited by analysing accuracy alongside inference latency, throughput, and data-cost trade-offs, providing guidance for both offline auditing and real-time edge monitoring. Further, to train the model, we introduce a physics-based simulated dataset featuring both attack and non-attack scenarios. Proposed models achieve up-to 83.4% classification accuracy with minimal false positives and negatives, demonstrating robust performance in identifying compromised quantum channels. This work represents a significant advancement in machine learning-assisted quantum security, providing a practical tool for enhancing the security of real-world QKD systems against stealthy photon-level attacks.
Quantum Key Distribution (QKD) techniques provide theoretically invulnerable security for cryptographic key exchange. However, hardware limitations, such as the use of weak coherent photon sources instead of a single-photon source, make it vulnerable to photon-number splitting (PNS) attacks. In a PNS attack Eve selectively intercepts multi-photon pulses while allowing single-photon pulses to pass through. PNS attacks do not affect the quantum bit error rate (QBER), rendering traditional QBER-based monitoring ineffective. Hence, to detect the attack in such cases, it becomes imperative to statistically monitor parameters such as photon counts at the detector, SKR, and shifted key length to identify the attack. In this paper, we propose two complementary deep learning-based frameworks for detection of the PNS attack in the QKD setup. The first operates directly on the raw photon sequence recorded at the receiver, and is realised as a 1-D convolutional network as well as a deeper residual 1-D CNN. The second operates on a compact 13-dimensional feature vector derived from photon statistics, secure-key length, and protocol scalars, and is realised as both a baseline feed-forward network and a deeper residual ANN with skip connections. Together, these four models let us study attack detection across two distinct input modalities. We further establish where each model is best suited by analysing accuracy alongside inference latency, throughput, and data-cost trade-offs, providing guidance for both offline auditing and real-time edge monitoring. Further, to train the model, we introduce a physics-based simulated dataset featuring both attack and non-attack scenarios. Proposed models achieve up-to 83.4% classification accuracy with minimal false positives and negatives, demonstrating robust performance in identifying compromised quantum channels. This work represents a significant advancement in machine learning-assisted quantum security, providing a practical tool for enhancing the security of real-world QKD systems against stealthy photon-level attacks.
Quantum Key Distribution (QKD) techniques provide theoretically invulnerable security for cryptographic key exchange. However, hardware limitations, such as the use of weak coherent photon sources instead of a single-photon source, make it vulnerable to photon-number splitting (PNS) attacks. In a PNS attack Eve selectively intercepts multi-photon pulses while allowing single-photon pulses to pass through. PNS attacks do not affect the quantum bit error rate (QBER), rendering traditional QBER-based monitoring ineffective. Hence, to detect the attack in such cases, it becomes imperative to statistically monitor parameters such as photon counts at the detector, SKR, and shifted key length to identify the attack. In this paper, we propose two complementary deep learning-based frameworks for detection of the PNS attack in the QKD setup. The first operates directly on the raw photon sequence recorded at the receiver, and is realised as a 1-D convolutional network as well as a deeper residual 1-D CNN. The second operates on a compact 13-dimensional feature vector derived from photon statistics, secure-key length, and protocol scalars, and is realised as both a baseline feed-forward network and a deeper residual ANN with skip connections. Together, these four models let us study attack detection across two distinct input modalities. We further establish where each model is best suited by analysing accuracy alongside inference latency, throughput, and data-cost trade-offs, providing guidance for both offline auditing and real-time edge monitoring. Further, to train the model, we introduce a physics-based simulated dataset featuring both attack and non-attack scenarios. Proposed models achieve up-to 83.4% classification accuracy with minimal false positives and negatives, demonstrating robust performance in identifying compromised quantum channels. This work represents a significant advancement in machine learning-assisted quantum security, providing a practical tool for enhancing the security of real-world QKD systems against stealthy photon-level attacks.
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.
The BB84 protocol is fundamental to quantum-secure communications, yet its extension to multi-receiver networks remains underexplored. This study addresses this gap by implementing a dual-receiver BB84 framework in Qiskit to evaluate security against intercept–resend and photon-number-splitting (PNS) attacks. Our methodology incorporates weak coherent pulses and realistic channel imperfections. Key findings show that intercept–resend attacks induce a detectable (~25%) increase in QBER, while PNS attacks allow a 100% gain in eavesdropper information with less than 2.5% QBER—revealing a critical vulnerability, which highlights the importance of a true single-photon source. The findings emphasize the suitability of BB84 for multiparty QKD scenarios, either as a decoy-state mechanism for enhanced eavesdropping detection or as a direct secure communication protocol.
Quantum key distribution (QKD) is an innovative technology, which exploits the laws of quantum mechanics to generate and distribute unconditionally secure shared cryptographic keying material between two geographically separated parties. The unique nature of QKD that ensures eavesdropping on the key distribution channel necessarily introduces detectable errors and shows promise for high-security environments, such as banking, government, and military. However, QKD systems are vulnerable to advanced theoretical and experimental attacks. In this paper, the photon number splitting (PNS) attack is studied in a specialized QKD modeling and simulation framework. First, a detailed treatment of the PNS attack is provided with emphasis on practical considerations, such as performance limitations and realistic sources of error. Second, ideal and non-ideal variations of the PNS attack are studied to measure the eavesdropper's information gain on the QKD-generated secret key bits and examine the detectability of PNS attacks with respect to both quantum bit error rate and the decoy state protocol. Finally, this paper provides a repeatable methodology for efficiently studying advanced attacks, both realized and notional, against QKD systems and more generally quantum communication protocols.
For a start, Quantum Key Distribution offers security not depending on any fundamental assumption. However, actual realizations choose to use weak coherent pulses as photon sources, rather than the ideal single-photon state, which bears security weaknesses due to the emission of sporadic multi-photon states. These states can be used in Photon-Number Splitting (PNS) attacks, where the attacker intercepts and buffers photons of multi-photon pulses and forwards the rest, enabling partial recovery of the key without inducing detectable perturbations. This article presents a simulation-based approach to analyze PNS attacks with realistic channel conditions like losses, detector imperfections, and finite key lengths. The research also examines the performance of decoy-state countermeasures, that use variable-intensity pulses to statistically reveal eavesdropping and Simulation results confirm the dominant character of PNS on raw key rates for the no-countermeasure scenario and ensure optimal decoy-state schemes restore security by cutting single-photon contributions. Results establish that although WCP QKD is vulnerable to PNS attacks in theory, strict adoption of decoy-state protocols aided with monitoring and finite-key analysis can provide immunity against an adversary. The paper emphasizes the need for simulation-based, implementation-dependent security analysis in direction towards well-designed practical quantum cryptographic systems. [1] [2] [3] [4] [10] [8]
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.