Generating differentially private (DP) synthetic data that closely resembles the original
private data is a scalable way to mitigate privacy concerns in the current data-driven world …

Differential Privacy (DP) image data synthesis, which leverages the DP technique to
generate synthetic data to replace the sensitive data, allowing organizations to share and …

Diffusion models (DMs) are widely used for generating high-quality high-dimensional
images in a non-differentially private manner. To address this challenge, recent papers …

Maximum mean discrepancy (MMD) is a particularly useful distance metric for differentially
private data generation: when used with finite-dimensional features it allows us to …

Differential Privacy (DP) image data synthesis, which leverages the DP technique to
generate synthetic data to replace the sensitive data, allowing organizations to share and …

Utilizing sensitive images (eg, human faces) for training DL models raises privacy concerns.
One straightforward solution is to replace the private images with synthetic ones generated …

Safeguarding privacy in sensitive training data is paramount, particularly in the context of
generative modeling. This is done through either differentially private stochastic gradient …

Text-to-image diffusion models have been shown to suffer from sample-level memorization,
possibly reproducing near-perfect replica of images that they are trained on, which may be …

Differentially private synthetic data is a promising alternative for sensitive data release. Many
differentially private generative models have been proposed in the literature. Unfortunately …

Differentially Private Stochastic Gradient Descent (DPSGD) is widely utilized to preserve
training data privacy in deep learning, which first clips the gradients to a predefined norm …