Quantum key distribution (QKD) is a technique that allows two distant parties to distribute and share a common secret, which then can be used as a cryptographic key. While mathematical proofs verify the security of perfectly implemented systems, imperfections in real devices allow attackers to retrieve information. This study uses machine-learning techniques to investigate information leakage via radio-frequency emissions of QKD device electronics. The approach allows researchers and engineers to harden devices against attacks.
Quantum key distribution (QKD) is a technique that allows two distant parties to distribute and share a common secret, which then can be used as a cryptographic key. While mathematical proofs verify the security of perfectly implemented systems, imperfections in real devices allow attackers to retrieve information. This study uses machine-learning techniques to investigate information leakage via radio-frequency emissions of QKD device electronics. The approach allows researchers and engineers to harden devices against attacks.
While quantum key distribution (QKD) protocols are proven secure based on fundamental physical laws, side channels may allow an eavesdropper to obtain information unnoticeably. We present a profiled [1] side-channel attack using a deep convolutional neural network to analyze the classical, radio-frequency electromagnetic emissions from the electronics of a QKD sender. At a few centimeters from the device, we are able to recover virtually all information about the secret key. Furthermore, we can still observe traces of electromagnetic radiation from the device at distances of a few meters using a wideband antenna. Our methods are designed to be easily adaptable and may serve as a starting point for assessing the presence of this side channel for other devices.
The Quantum Key Distribution (QKD) method leverages the principles of quantum mechanics to securely create and distribute private keys using quantum systems and an authenticated public classical channel. Despite offering informationtheoretical security, its physical implementations often suffer from unintended information leakage, known as side channels, which eavesdroppers can exploit to obtain the private key. This study introduces a classical-side-channel attack on the privacyamplification step of a general QKD protocol based on matrix hashing, utilizing machine-learning techniques to analyze powerconsumption leakage. Through multiple simulated scenarios, the study found that the gradient-boosting machine consistently outperformed other models, recovering the entire private key for high measuring-instrument sampling rates, regardless of the hashing matrix size and noise level tested. Additionally, the study proposes a strategy based on analyzing the confusion matrices of the model to facilitate a brute-force search for the critical feasible in the case of a non-perfect model. Furthermore, the study discusses countermeasures such as noise insertion, masking, and randomization techniques, potentially restoring the QKD protocol's information-theoretical security. This work demonstrates that machine-learning techniques can effectively characterize the leakages in a QKD implementation and create potent attacks.
Quantum key distribution (QKD) is widely regarded as a highly secure quantum encryption approach since it applies theoretical principles of quantum mechanics as a medium of security, unlike classical encryption processes that rely on complex mathematics. However, practical QKD systems are vulnerable due to imperfect photon source hardware, communication channel, and detector implementation. These hardware imperfections open side channels that an adversary can exploit without violating principles of quantum mechanics. This review provides a comprehensive overview of the current QKD protocols, quantum hacking strategies and their operating principles, vulnerable hardware components and their mitigation techniques. This paper further investigates how state-of-the-art paradigms based on artificial intelligence (AI) and machine learning (ML), along with key subfields—such as deep learning (DL), deep reinforcement learning (DRL), and quantum machine learning (QML)—are reshaping the domain. In particular, this paper analyzes their dual roles as enablers of sophisticated attacks and as instruments for attack detection and mitigation. By jointly addressing the challenges in quantum communication and adaptive learning, as well as attack and detection architectures, this survey elucidates both the capabilities and the limitations of contemporary attack-detection mechanisms in the field. This survey seeks to establish a unified framework that conceptually integrates physical-layer quantum hacking with AI-/ML-based security, emphasizing their dual function as both an intelligent defensive layer and a potential tool for advanced threats.
Quantum key distribution (QKD) offers information-theoretical security, while real systems are thought not to promise practical security effectively. In the practical continuous-variable (CV) QKD system, the deviations between realistic devices and idealized models might introduce vulnerabilities for eavesdroppers and stressors for two parties. However, the common quantum hacking strategies and countermeasures inevitably increase the complexity of practical CV systems. Machine-learning techniques are utilized to explore how to perceive practical imperfections. Here, we review recent works on secure CVQKD systems with machine learning, where the methods for detections and attacks were studied.
Quantum Key Distribution (QKD) promises information-theoretic security based on the fundamental laws of quantum mechanics. However, practical implementations deviate from idealized models and are therefore susceptible to side-channel attacks that exploit physical imperfections rather than theoretical vulnerabilities. Over the past two decades, a wide range of attacks have been demonstrated against QKD systems, including those targeting detectors, sources, timing information, power consumption, and electromagnetic emissions. This paper addresses a selection of a few side-channel attacks reported in the literature, classifying them according to their underlying physical mechanisms and attack strategies. We analyze their impact on the security of different QKD protocols and platforms, and highlight how experimental demonstrations have shaped the community's understanding of implementation security. In addition, we present and evaluate mitigation techniques proposed to date, such as device-independent and measurement-device-independent QKD, hardware countermeasures, monitoring strategies, and so on. We also identify open challenges and promising directions for enhancing the robustness of future quantum communication systems.
Abstract While quantum key distribution (QKD) is a theoretically secure way of growing quantum-safe encryption keys, many practical implementations are challenged due to various open attack vectors, resulting in many variations of QKD protocols. Side channels are one such vector that allows a passive or active eavesdropper to obtain QKD information leaked through practical devices. This paper assesses the feasibility and implications of extracting the raw secret key from far-field radiated emissions from the single-photon avalanche diodes used in a BB84 QKD quad-detector receiver. Enhancement of the attack was also demonstrated through the use of deep-learning model to distinguish radiated emissions due to the four polarized encoding states. To evaluate the severity of such side-channel attack, multi-class classification based on raw-data and pre-processed data is implemented and assessed. Results show that classifiers based on both raw-data and pre-processed features can discern variations of the electromagnetic emissions caused by specific orientations of the detectors within the receiver with an accuracy higher than 90%. This research proposes machine learning models as a technique to assess EM information leakage risk of QKD and highlights the feasibility of side-channel attacks in the far-field region, further emphasizing the need to utilise mechanisms to avoid electromagnetic radiation information leaks and measurement-device-independent QKD protocols.