Related papers: Privately generating tabular data using language m…

Differentially private (DP) language model inference is an approach for generating private synthetic text. A sensitive input example is used to prompt an off-the-shelf large language model (LLM) to produce a similar example. Multiple…

Differentially Private Synthetic Data Generation (DP-SDG) is a key enabler of private and secure tabular-data sharing, producing artificial data that carries through the underlying statistical properties of the input data. This typically…

The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution…

Differential privacy is a robust privacy standard that has been successfully applied to a range of data analysis tasks. Despite much recent work, optimal strategies for answering a collection of correlated queries are not known. We study…

Data privacy protection studies how to query a dataset while preserving the privacy of individuals whose sensitive information is contained in the dataset. The information privacy model protects the privacy of an individual by using a noisy…

Graph data is used in a wide range of applications, while analyzing graph data without protection is prone to privacy breach risks. To mitigate the privacy risks, we resort to the standard technique of differential privacy to publish a…

We show that differential privacy type guarantees can be obtained when using a Poisson synthesis mechanism to protect counts in contingency tables. Specifically, we show how to obtain $(\epsilon, \delta)$-probabilistic differential privacy…

In this work we explore deep generative models of text in which the latent representation of a document is itself drawn from a discrete language model distribution. We formulate a variational auto-encoder for inference in this model and…

Recent advances in generating synthetic data that allow to add principled ways of protecting privacy -- such as Differential Privacy -- are a crucial step in sharing statistical information in a privacy preserving way. But while the focus…

Synthetic tabular data generation has emerged as a promising method to address limited data availability and privacy concerns. With the sharp increase in the performance of large language models in recent years, researchers have been…

Data privacy is an increasingly important aspect of many real-world Data sources that contain sensitive information may have immense potential which could be unlocked using the right privacy enhancing transformations, but current methods…

Linear models are ubiquitous in data science, but are particularly prone to overfitting and data memorization in high dimensions. To guarantee the privacy of training data, differential privacy can be used. Many papers have proposed…

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

Machine learning (ML) models frequently rely on training data that may include sensitive or personal information, raising substantial privacy concerns. Legislative frameworks such as the General Data Protection Regulation (GDPR) and the…

Generative AI offers transformative potential for high-stakes domains such as healthcare and finance, yet privacy and regulatory barriers hinder the use of real-world data. To address this, differentially private synthetic data generation…

Differential privacy is a framework for privately releasing summaries of a database. Previous work has focused mainly on methods for which the output is a finite dimensional vector, or an element of some discrete set. We develop methods for…

Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning…

Data serves as the fundamental foundation for advancing deep learning, particularly tabular data presented in a structured format, which is highly conducive to modeling. However, even in the era of LLM, obtaining tabular data from sensitive…

Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared…

As synthetic data becomes increasingly popular in machine learning tasks, numerous methods--without formal differential privacy guarantees--use synthetic data for training. These methods often claim, either explicitly or implicitly, to…