This work introduces a novel distributed Quantum Machine Learning (QML) scheme that integrates differential privacy methods to enable secure and efficient classification. The approach begins with the computation of an embedding that, given a seed, is randomly segmented into multiple sub-vectors. Each segment is perturbed with noise to enforce differential privacy and is then reduced in dimensionality via Principal Component Analysis (PCA). This PCA addresses the parameter limitations of QML. The reduced embeddings are distributed to multiple QML centers, where they are processed by a QML classifier. To obtain a final prediction, individual decisions from each center are combined through an aggregation mechanism. All classical information communications between the server and QML centers are encrypted and protected by a Quantum Key Distribution (QKD) network between these nodes. This scheme enables training and inference in distributed QML settings while robustly preserving privacy. Empirical evaluations show that the method maintains competitive accuracy with fewer quantum resources, paving the way for practical and scalable deployments of QML in real-world quantum computing context.
This work introduces a novel distributed Quantum Machine Learning (QML) scheme that integrates differential privacy methods to enable secure and efficient classification. The approach begins with the computation of an embedding that, given a seed, is randomly segmented into multiple sub-vectors. Each segment is perturbed with noise to enforce differential privacy and is then reduced in dimensionality via Principal Component Analysis (PCA). This PCA addresses the parameter limitations of QML. The reduced embeddings are distributed to multiple QML centers, where they are processed by a QML classifier. To obtain a final prediction, individual decisions from each center are combined through an aggregation mechanism. All classical information communications between the server and QML centers are encrypted and protected by a Quantum Key Distribution (QKD) network between these nodes. This scheme enables training and inference in distributed QML settings while robustly preserving privacy. Empirical evaluations show that the method maintains competitive accuracy with fewer quantum resources, paving the way for practical and scalable deployments of QML in real-world quantum computing context.
Quantum Machine Learning (QML) is becoming increasingly prevalent due to its potential to enhance classical machine learning (ML) tasks, such as classification. Although quantum noise is often viewed as a major challenge in quantum computing, it also offers a unique opportunity to enhance privacy. In particular, intrinsic quantum noise provides a natural stochastic resource that, when rigorously analyzed within the differential privacy (DP) framework and composed with classical mechanisms, can satisfy formal (ε,δ)-DP guarantees. This enables a reduction in the required classical perturbation without compromising the privacy budget, potentially improving model utility. However, the integration of classical and quantum noise for privacy preservation remains unexplored. In this work, we propose a hybrid noise-added mechanism, HYPER-Q, that combines classical and quantum noise to protect the privacy of QML models. We provide a comprehensive analysis of its privacy guarantees and establish theoretical bounds on its utility. Empirically, we demonstrate that HYPER-Q outperforms existing classical noise-based mechanisms in terms of adversarial robustness across multiple real-world datasets.
The mix of quantum computing and machine learning has introduced strong quantum models able to resolve challenging tasks efficiently. Still, the use of centralized QML systems could present challenges with privacy because sharing quantum data with untrusted aggregators is especially risky. This study describes a method called Privacy-Preserving Quantum Federated Learning (PQFL), which allows multiple clients to jointly train quantum models while maintaining data confidentiality. This system offers security by combining QHE and QDP to cover the processes of aggregating protected models and enforcing privacy on the data. Hybrid quantum-classical studies reveal that PQFL is both accurate and advanced in protecting privacy and communication security. According to these results, PQFL works effectively in privacy-friendly domains including healthcare, genomics, and finance, where data needs to be managed securely.
Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. There exists the potential for a quantum advantage due to the intractability of quantum operations on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information, but to the best of our knowledge, no current QML models are equipped with privacy-preserving features. This raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has not been thoroughly studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without signficiantly diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices [noisy intermediate-scale quantum (NISQ)]. The approach's success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.
As quantum machine learning (QML) continues to evolve, it promises unparalleled computational advantages in processing complex data. However, the rise of QML also introduces critical concerns regarding data security and privacy, particularly in sensitive domains such as healthcare, finance, and defense. Classical cryptographic methods fall short in addressing threats that arise in quantum communication and computation environments. To bridge this gap, this paper presents a hybrid framework that integrates quantum cryptography—specifically Quantum Key Distribution (QKD)—with QML pipelines, ensuring end-to-end quantum-secure machinelearning operations. We first construct a theoretical model that outlines how QKD can be effectively embedded into a typical QML workflow to mitigate adversarial threats such as eavesdropping, model inversion, and poisoning attacks. We then implement this framework using IBM’s Qiskit and a simulated QKD environment via QuNetSim, applying it to a quantum support vector machine (qSVM) classifier. The integration is evaluated based on accuracy, computational overhead, and communication latency. Our results indicate that quantum-secured QML systems can maintain robust model performance while significantly enhancing data confidentiality. This work lays the groundwork for future developments in secure quantum artificial intelligence infrastructures.
Quantum federated learning (QFL) enables collaborative training of quantum machine learning (QML) models across distributed quantum devices without raw data exchange. However, QFL remains vulnerable to adversarial attacks, where shared QML model updates can be exploited to undermine information privacy. In the context of noisy intermediate-scale quantum (NISQ) devices, a key question arises: How can inherent quantum noise be leveraged to enforce differential privacy (DP) and protect model information during training and communication? This paper explores a novel DP mechanism that harnesses quantum noise to safeguard quantum models throughout the QFL process. By tuning noise variance through measurement shots and depolarizing channel strength, our approach achieves desired DP levels tailored to NISQ constraints. Simulations demonstrate the framework's effectiveness by examining the relationship between differential privacy budget and noise parameters, as well as the trade-off between security and training accuracy. Additionally, we demonstrate the framework's robustness against an adversarial attack designed to compromise model performance using adversarial examples, with evaluations based on critical metrics such as accuracy on adversarial examples, confidence scores for correct predictions, and attack success rates. The results reveal a tunable trade-off between privacy and robustness, providing an efficient solution for secure QFL on NISQ devices with significant potential for reliable quantum computing applications.
Quantum machine learning (QML) is increasingly recognized as one of the most promising near-term applications of quantum computing, viewed as a next-frontier candidate beyond purely classical approaches. Hybrid quantum-classical models operationalize this potential by embedding a parameterized quantum circuit within a model where all other components remain classical-a design already applied to chemistry simulation, financial modeling, and image classification. However, their deployment in privacy-sensitive, multi-party settings is constrained by the need to avoid centralizing raw data and by the requirement that modern quantum circuits remain parameter-efficient to stay trainable at scale. In this paper, we address these constraints by evaluating federated learning (FL) as a means of combining a hybrid quantum-classical active party with a classical passive party, using Sherpa.ai's Blind Vertical FL (SBVFL) protocol to avoid centralizing raw data, while drastically reducing communication. We construct the split multiplicative periodic parity (SMPP) benchmark, following common QML design practice. On this task, our simulations show that SBVFL raises accuracy from 0.7227 to 0.8757 compared to local training, closely approaching non-private centralized accuracy, and that the hybrid quantum-classical model achieves this with substantially fewer trainable parameters than the classical neural networks and random forest alternatives. These results show that FL enables high-performing, privacy-preserving quantum-classical collaboration without centralizing raw data.