Abstract How to ensure privacy security and improve computing efficiency is a research hotspot in the field of machine learning. Among them, how to balance the interests of users, cloud servers and attackers on the premise of ensuring user privacy is a difficult problem in the field of machine learning privacy protection. The development of quantum computing breaks through the computational bottleneck of classical machine learning and has derived the research direction of quantum machine learning. At present, hybrid quantum–classical machine learning in NISQ era has become a research hotspot, but researchers rarely pay attention to the privacy protection in quantum machine learning. Therefore, this paper is the first to apply game theory to the privacy protection in quantum machine learning and proposes the privacy game model of user - server - attacker in Hybrid Classical Quantum BP Neural Network (HCQBPNN). Different from previous studies, this paper sets game strategies based on users’ privacy requirements in practical applications, and aims to maximize the interests of attackers, cloud servers and users. The experiment proves that users can use the privacy game model proposed in this paper to get the optimal privacy combination strategy, and at the same time make the cloud server and the attacker can obtain positive income.
Abstract How to ensure privacy security and improve computing efficiency is a research hotspot in the field of machine learning. Among them, how to balance the interests of users, cloud servers and attackers on the premise of ensuring user privacy is a difficult problem in the field of machine learning privacy protection. The development of quantum computing breaks through the computational bottleneck of classical machine learning and has derived the research direction of quantum machine learning. At present, hybrid quantum–classical machine learning in NISQ era has become a research hotspot, but researchers rarely pay attention to the privacy protection in quantum machine learning. Therefore, this paper is the first to apply game theory to the privacy protection in quantum machine learning and proposes the privacy game model of user - server - attacker in Hybrid Classical Quantum BP Neural Network (HCQBPNN). Different from previous studies, this paper sets game strategies based on users’ privacy requirements in practical applications, and aims to maximize the interests of attackers, cloud servers and users. The experiment proves that users can use the privacy game model proposed in this paper to get the optimal privacy combination strategy, and at the same time make the cloud server and the attacker can obtain positive income.
Abstract Machine learning algorithms help us discover knowledge from big data. Data used for training or prediction often contain private information about users. Discovering knowledge while protecting data or user privacy is the way machine learning is expected, especially in the cloud environment. Quantum machine learning is a kind of machine learning that realizes parallel acceleration by quantum superposition. Quantum computing power for quantum machine learning is typically provided by quantum cloud computing services. Existing quantum machine learning algorithms hardly consider privacy protection. This paper presents an encryption method for image data which can effectively protect the input data privacy in hybrid quantum–classical convolutional neural networks algorithm. The user’s original image data is first encrypted, and then sent to the quantum cloud to calculate the image convolution. By doing so, the feature map of the ciphertext image is obtained by the user. The result obtained by decrypting the feature map is the same as that obtained by using the original image as the input of convolution calculation. Experiments show that our privacy protection scheme can protect the privacy of input image data in the hybrid quantum–classical neural networks algorithm, but does not affect the accuracy of the algorithm. In addition to image encryption and feature map decryption, the proposed scheme does not bring additional computational complexity.
Abstract Quantum machine learning is expected to utilize the potential advantages of quantum computing to advance the efficiency of machine learning. However, with the help of quantum cloud servers, ordinary users may confront the threat of privacy leakage of input data and models when performing the training or inference of quantum neural networks (QNNs). To address this problem, we present a new framework that allows the training and inference of delegated QNNs to be performed on encrypted data to protect the privacy of users’ data and models. This framework contains two models that are alternately trained: an encryptor and a predictor. The classical client first trains the encryptor defined by a classical neural network to map plaintext input data to vastly different ciphertext data. The ciphertext data is sent to the quantum cloud server to train the predictor defined by a QNN, which can indirectly predict the labels of plaintext data. With the trained encryptor and predictor, the client can send the encrypted data to the server for prediction and obtain almost equivalent prediction results. The proposed framework is applied to three types of QNN models, each dealing with low-dimensional tabular data, image data, and one-dimensional time series data, respectively. Experimental results show that the privacy protection method based on our framework can protect data and model privacy without degrading the performance of QNNs. The framework does not require users to have quantum capabilities and is suitable for protecting data and model privacy for various QNN models.
Abstract It takes a lot of computational resources to train a machine learning model. So does quantum machine learning. In the NISQ (Noisy Intermediate Scale Quantum) era, there is a need for users who cannot afford quantum computers to utilize quantum servers to complete quantum machine learning with protection privacy of data and model parameters. In this paper, novel homomorphic encryption methods and circuit design with hidden parameter for R z , R x and R y gate are putting forward. Based on which, we further propose quantum neural network (QNN) with privacy protection of input data and training parameters, where hiding model parameters has hardly mentioned in existing literature. To verify the validity of the proposed scheme, we conducted experiments on MNIST and Iris datasets, and obtained losses and accuracy that are almost identical to the original algorithms. Experiments show that our scheme can protect privacy well in the training and have no effect on accuracy of the algorithm. By comparison, the proposed scheme is more secure than most existing literature and requires less extra complexity O(4n).
Quantum Machine Learning (QML) has shown rapid advances by utilizing quantum computing for machine learning tasks. Meanwhile, the privacy risks accompanying QML is also starting to be studied, which inherit privacy leakage channels from "classical" ML and also quantum-unique risks. Existing work on privacy-preserving QML largely focuses on a QML-as-a-service scenario, which generally assumes that the QML model owner provides only classical bit outputs to queries, while users (and adversaries) have only classical computing abilities. However, this view is increasingly challenged in a quantum-native world of quantum-capable users/adversaries, which may have access to both quantum computing abilities and access to quantum information output from service providers.
In this paper, we aim to bridge this gap by examining membership inference attacks against QML models by demonstrating that increasing quantum access and quantum computing abilities provides provable theoretical privacy leakage and empirical adversarial gain. However, the probabilistic nature of QML introduces a gap between theoretical and empirical adversarial advantage. These results show that existing research on privacy leakage in QML models underestimates privacy leakage in emergent quantum-native access regimes, and we hope to establish a first step in examining potential privacy leakages for QML in the quantum-native world.
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.
Abstract Quantum machine learning (QML) is an emerging field of research with potential applications to distributed collaborative learning, such as split learning (SL). SL allows resource-constrained clients to collaboratively train ML models with a server, reduce their computational overhead, and enable data privacy by avoiding raw data sharing. Although QML with SL has been studied, the problem remains open in resource-constrained environments where clients lack quantum computing capabilities. Additionally, data privacy leakage between client and server in SL poses risks of reconstruction attacks on the server side. To address these issues, we propose hybrid quantum split learning (HQSL), an application of hybrid QML in SL. HQSL enables classical clients to train models with a hybrid quantum server and curtails reconstruction attacks. Additionally, we introduce a novel qubit-efficient data-loading technique for designing a quantum layer in HQSL, minimizing both the number of qubits and circuit depth. Evaluations on real hardware demonstrate HQSL’s practicality under realistic quantum noise. Experiments on five datasets demonstrate HQSL’s feasibility and ability to enhance classification performance compared to its classical models. Notably, HQSL achieves mean improvements of over 3% in both accuracy and F1-score for the Fashion-MNIST dataset and over 1.5% in both metrics for the Speech Commands dataset. We expand these studies to include up to 100 clients, confirming HQSL’s scalability. Moreover, we introduce a noise-based defense mechanism to tackle reconstruction attacks on the server side. Overall, HQSL enables classical clients to train collaboratively with a hybrid quantum server, improving model performance and resistance against reconstruction attacks.