Abstract Quantum neural networks (QNN) hold the potential for quantum advantages but are confronted with privacy leakage risks that could undermine users’ benefits. To address this issue, we propose an enhanced QNN model integrated with differential privacy. After converting classical data into quantum states using encoding circuit, we apply data re-uploading technology to embed the encoding circuit multiple times into the overall circuit. The classification outcomes are derived by measuring the final quantum state. During the optimization process of QNN, we introduce Gaussian noise into the gradient of the loss function to ensure differential privacy. Our theoretical analysis demonstrates that in differential privacy settings, the model effectively protects privacy while demonstrating good performance. Our experimental analysis demonstrates that on four standard datasets, our model achieves the same accuracy as classical neural network (NN) while utilizing only 22% of the parameters of NN, and exhibiting lower performance loss compared to other QNN.
Abstract Quantum neural networks (QNN) hold the potential for quantum advantages but are confronted with privacy leakage risks that could undermine users’ benefits. To address this issue, we propose an enhanced QNN model integrated with differential privacy. After converting classical data into quantum states using encoding circuit, we apply data re-uploading technology to embed the encoding circuit multiple times into the overall circuit. The classification outcomes are derived by measuring the final quantum state. During the optimization process of QNN, we introduce Gaussian noise into the gradient of the loss function to ensure differential privacy. Our theoretical analysis demonstrates that in differential privacy settings, the model effectively protects privacy while demonstrating good performance. Our experimental analysis demonstrates that on four standard datasets, our model achieves the same accuracy as classical neural network (NN) while utilizing only 22% of the parameters of NN, and exhibiting lower performance loss compared to other QNN.
Quantum convolutional neural networks hold potential advantages for image recognition by exploiting unique quantum properties. However, their training processes remain susceptible to privacy leakage. To address this issue, we propose a hybrid quantum convolutional neural network (HQCNN) model with differential privacy. This architecture utilizes quantum superposition and entanglement to efficiently extract image features. To ensure differential privacy, Gaussian noise is added to the parameter gradients. Crucially, the superior feature extraction and learning capabilities of the HQCNN are utilized to mitigate the performance degradation typically induced by noise injection. Experiments on the MNIST and Fashion-MNIST datasets demonstrate that the proposed model achieves a test accuracy exceeding 95% under a strict privacy budget of ɛ < 1.04. Furthermore, evaluations on the CIFAR-10 dataset confirm the feasibility of the model in the differentially private scenario. Comparative analyses further validate that the proposed model preserves privacy while maintaining superior performance in differentially private training.
The stochastic nature of renewable energy and load demand requires efficient and accurate solutions for probabilistic optimal power flow (OPF). Quantum neural networks (QNNs), which combine quantum computing and machine learning, offer computational advantages in approximating OPF by effectively handling high-dimensional data. However, adversaries with access to non-private OPF solutions can potentially infer sensitive load demand patterns, raising significant privacy concerns. To address this issue, we propose a privacy-preserving QNN model for probabilistic OPF approximation. By incorporating Gaussian noise into the training process, the learning algorithm achieves (ɛ, δ)-differential privacy with theoretical guarantees. Moreover, we develop a strongly entangled quantum state to enhance the nonlinearity expressiveness of the QNN. Experimental results demonstrate that the proposed method successfully prevents privacy leakage without compromising the statistical properties of probabilistic OPF. Moreover, compared to classical private neural networks, the QNN reduces the number of parameters by 90% while achieving significantly higher accuracy and greater stability.
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.
Upon integrating Quantum Neural Network (QNN) as the local model, Quantum Federated Learning (QFL) has recently confronted notable challenges. Firstly, exploration is hindered over sharp minima, decreasing learning performance. Secondly, the steady gradient descent results in more stable and predictable model transmissions over wireless channels, making the model more susceptible to attacks from adversarial entities. Additionally, the local QFL model is vulnerable to noise produced by the quantum device's intermediate noise states, since it requires the use of quantum gates and circuits for training. This local noise becomes intertwined with learning parameters during training, impairing model precision and convergence rate. To address these issues, we propose a new QFL technique that incorporates differential privacy and introduces a dedicated noise estimation strategy to quantify and mitigate the impact of intermediate quantum noise. Furthermore, we design an adaptive noise generation scheme to alleviate privacy threats associated with the vanishing gradient variance phenomenon of QNN and enhance robustness against device noise. Experimental results demonstrate that our algorithm effectively balances convergence, reduces communication costs, and mitigates the adverse effects of intermediate quantum noise while maintaining strong privacy protection. Using real-world datasets, we achieved test accuracy of up to 98.47% for the MNIST dataset and 83.85% for the CIFAR-10 dataset while maintaining fast execution times.
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 computing revolutionizes the way of solving complex problems and handling vast datasets, which shows great potential to accelerate the machine learning process. However, data leakage in quantum machine learning (QML) may present privacy risks. Although differential privacy (DP), which protects privacy through the injection of artificial noise, is a well-established approach, its application in the QML domain remains under-explored. In this paper, we propose to harness inherent quantum noises to protect data privacy in QML. Especially, considering the Noisy Intermediate-Scale Quantum (NISQ) devices, we leverage the unavoidable shot noise and incoherent noise in quantum computing to preserve the privacy of QML models for binary classification. We mathematically analyze that the gradient of quantum circuit parameters in QML satisfies a Gaussian distribution, and derive the upper and lower bounds on its variance, which can potentially provide the DP guarantee. Through simulations, we show that a target privacy protection level can be achieved by running the quantum circuit a different number of times.