Related papers: DPAF: Image Synthesis via Differentially Private A…

We propose a differentially private data generation paradigm using random feature representations of kernel mean embeddings when comparing the distribution of true data with that of synthetic data. We exploit the random feature…

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 undesirable. To remedy this issue, we develop the first…

Machine learning practitioners frequently seek to leverage the most informative available data, without violating the data owner's privacy, when building predictive models. Differentially private data synthesis protects personal details…

Federated learning seeks to address the issue of isolated data islands by making clients disclose only their local training models. However, it was demonstrated that private information could still be inferred by analyzing local model…

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both…

Generating synthetic datasets for training face recognition models is challenging because dataset generation entails more than creating high fidelity images. It involves generating multiple images of same subjects under different factors…

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…

Synthetic data generation has become an emerging tool to help improve the adversarial robustness in classification tasks since robust learning requires a significantly larger amount of training samples compared with standard classification…

The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data…

Recent success of deep neural networks (DNNs) hinges on the availability of large-scale dataset; however, training on such dataset often poses privacy risks for sensitive training information. In this paper, we aim to explore the power of…

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…

The advent of location-based services has led to the widespread adoption of indoor localization systems, which enable location tracking of individuals within enclosed spaces such as buildings. While these systems provide numerous benefits…

Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs). Traditional image-to-image translation networks can…

Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve…

Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher. In fact, the key challenge in generating variable-scale…

Federated learning (FL) faces two primary challenges: the risk of privacy leakage due to parameter sharing and communication inefficiencies. To address these challenges, we propose DPSFL, a federated learning method that utilizes…

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public. Even though differential privacy (DP) is a widely accepted…

The interest of the deep learning community in image synthesis has grown massively in recent years. Nowadays, deep generative methods, and especially Generative Adversarial Networks (GANs), are leading to state-of-the-art performance,…

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…