Related papers: Privacy-preserving Data Sharing on Vertically Part…

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis. If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to…

Decentralized stochastic optimization is the basic building block of modern collaborative machine learning, distributed estimation and control, and large-scale sensing. Since involved data usually contain sensitive information like user…

Data privacy is a core tenet of responsible computing, and in the United States, differential privacy (DP) is the dominant technical operationalization of privacy-preserving data analysis. With this study, we qualitatively examine one class…

Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects. Differential privacy (DP) has become established as a standard for protecting learning results. The…

Existing differentially private (DP) synthetic data generation mechanisms typically assume a single-source table. In practice, data is often distributed across multiple tables with relationships across tables. In this paper, we introduce…

We give a fast algorithm to optimally compose privacy guarantees of differentially private (DP) algorithms to arbitrary accuracy. Our method is based on the notion of privacy loss random variables to quantify the privacy loss of DP…

Decentralized optimization is gaining increased traction due to its widespread applications in large-scale machine learning and multi-agent systems. The same mechanism that enables its success, i.e., information sharing among participating…

In many real-world applications of machine learning, data are distributed across many clients and cannot leave the devices they are stored on. Furthermore, each client's data, computational resources and communication constraints may be…

Many machine learning applications are based on data collected from people, such as their tastes and behaviour as well as biological traits and genetic data. Regardless of how important the application might be, one has to make sure…

Background: Synthetic data has been proposed as a solution for sharing anonymized versions of sensitive biomedical datasets. Ideally, synthetic data should preserve the structure and statistical properties of the original data, while…

Sharing sensitive data is vital in enabling many modern data analysis and machine learning tasks. However, current methods for data release are insufficiently accurate or granular to provide meaningful utility, and they carry a high risk of…

Machine learning (ML) models have been shown to leak private information from their training datasets. Differential Privacy (DP), typically implemented through the differential private stochastic gradient descent algorithm (DP-SGD), has…

Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a method for generating…

In privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) performs worse than SGD due to per-sample gradient clipping and noise addition. A recent focus in private learning research is improving the…

Despite several works that succeed in generating synthetic data with differential privacy (DP) guarantees, they are inadequate for generating high-quality synthetic data when the input data has missing values. In this work, we formalize the…

We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs). This framework can be used to take in…

Differential privacy (DP) has been accepted as a rigorous criterion for measuring the privacy protection offered by random mechanisms used to obtain statistics or, as we will study here, synthetic datasets from confidential data. Methods to…

As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient…

We consider the problem of generating private synthetic versions of real-world graphs containing private information while maintaining the utility of generated graphs. Differential privacy is a gold standard for data privacy, and the…

Within the machine learning community, reconstruction attacks are a principal concern and have been identified even in federated learning (FL), which was designed with privacy preservation in mind. In response to these threats, the privacy…