Related papers: Towards Biologically Plausible and Private Gene Ex…

Language modeling is a keystone task in natural language processing. When training a language model on sensitive information, differential privacy (DP) allows us to quantify the degree to which our private data is protected. However,…

Differential privacy (DP) has become a rigorous central concept for privacy protection in the past decade. We use Gaussian differential privacy (GDP) in gauging the level of privacy protection for releasing statistical summaries from data.…

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…

In differential privacy (DP), a challenging problem is to generate synthetic datasets that efficiently capture the useful information in the private data. The synthetic dataset enables any task to be done without privacy concern and…

Differentially private stochastic gradient descent (DP-SGD) is the canonical approach to private deep learning. While the current privacy analysis of DP-SGD is known to be tight in some settings, several empirical results suggest that…

Advances in generative models have transformed the field of synthetic image generation for privacy-preserving data synthesis (PPDS). However, the field lacks a comprehensive survey and comparison of synthetic image generation methods across…

Constructing a differentially private (DP) estimator requires deriving the maximum influence of an observation, which can be difficult in the absence of exogenous bounds on the input data or the estimator, especially in high dimensional…

When synthetic data is released, some individuals are harder to protect than others. A patient with a rare disease combination or a transaction with unusual characteristics stands out from the crowd. Differential privacy provides worst-case…

To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of…

To protect sensitive data in training a Generative Adversarial Network (GAN), the standard approach is to use differentially private (DP) stochastic gradient descent method in which controlled noise is added to the gradients. The quality of…

Motivation: Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymisation strategies fail to provide sufficient level of protection for genomic data, because the data…

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We develop a general theory that characterizes the worst-case privacy loss of an…

We initiate the study of language generation in the limit, a model recently introduced by Kleinberg and Mullainathan [KM24], under the constraint of differential privacy. We consider the continual release model, where a generator must…

Privacy protection with synthetic data generation often uses differentially private statistics and model parameters to quantitatively express theoretical security. However, these methods do not take into account privacy protection due to…

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…

Machine learning models have shone in a variety of domains and attracted increasing attention from both the security and the privacy communities. One important yet worrying question is: Will training models under the differential privacy…

Releasing full data records is one of the most challenging problems in data privacy. On the one hand, many of the popular techniques such as data de-identification are problematic because of their dependence on the background knowledge of…

Task-oriented dialogue systems often assist users with personal or confidential matters. For this reason, the developers of such a system are generally prohibited from observing actual usage. So how can they know where the system is failing…

Private synthetic data sharing is preferred as it keeps the distribution and nuances of original data compared to summary statistics. The state-of-the-art methods adopt a select-measure-generate paradigm, but measuring large domain…

Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We…