Related papers: Privacy-Preserving Inference in Machine Learning S…

Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…

The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical…

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and…

In the standard privacy-preserving Machine learning as-a-service (MLaaS) model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It…

The privacy of data is a major challenge in machine learning as a trained model may expose sensitive information of the enclosed dataset. Besides, the limited computation capability and capacity of edge devices have made cloud-hosted…

Edge intelligence enables resource-demanding Deep Neural Network (DNN) inference without transferring original data, addressing concerns about data privacy in consumer Internet of Things (IoT) devices. For privacy-sensitive applications,…

Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers…

Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from…

Prior work on differential privacy analysis of randomized SGD algorithms relies on composition theorems, where the implicit (unrealistic) assumption is that the internal state of the iterative algorithm is revealed to the adversary. As a…

Massive human-related data is collected to train neural networks for computer vision tasks. A major conflict is exposed relating to software engineers between better developing AI systems and distancing from the sensitive training data. To…

In this paper, we propose a novel Heterogeneous Gaussian Mechanism (HGM) to preserve differential privacy in deep neural networks, with provable robustness against adversarial examples. We first relax the constraint of the privacy budget in…

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…

We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…

We propose and analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution ($m…

We present a practical framework to deploy privacy-preserving machine learning (PPML) applications in untrusted clouds based on a trusted execution environment (TEE). Specifically, we shield unmodified PyTorch ML applications by running…

In this work, we investigate if statistical privacy can enhance the performance of ORAM mechanisms while providing rigorous privacy guarantees. We propose a formal and rigorous framework for developing ORAM protocols with statistical…

In the domain of cloud-based deep learning, the imperative for external computational resources coexists with acute privacy concerns, particularly identity leakage. To address this challenge, we introduce XNN and XNN-d, pioneering…

Alternating Direction Method of Multipliers (ADMM) is a widely used tool for machine learning in distributed settings, where a machine learning model is trained over distributed data sources through an interactive process of local…

The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…