Related papers: Differentially Private Imaging via Latent Space Ma…
Local differential privacy is a widely studied restriction on distributed algorithms that collect aggregates about sensitive user data, and is now deployed in several large systems. We initiate a systematic study of a fundamental limitation…
We propose new differential privacy solutions for when external \emph{invariants} and \emph{integer} constraints are simultaneously enforced on the data product. These requirements arise in real world applications of private data curation,…
Differential Privacy (DP) has become a gold standard in privacy-preserving data analysis. While it provides one of the most rigorous notions of privacy, there are many settings where its applicability is limited. Our main contribution is in…
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…
In this paper we present the Sampling Privacy mechanism for privately releasing personal data. Sampling Privacy is a sampling based privacy mechanism that satisfies differential privacy.
Face anonymization aims to protect sensitive identity information by altering faces while preserving visual realism and utility for downstream computer vision tasks. Current methods struggle to simultaneously ensure high image quality,…
StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing…
With the widespread sharing of personal face images in applications' public databases, face recognition systems faces real threat of being breached by potential adversaries who are able to access users' face images and use them to intrude…
In recent years, differential privacy has emerged as the de facto standard for sharing statistics of datasets while limiting the disclosure of private information about the involved individuals. This is achieved by randomly perturbing the…
Digital imaging systems have traditionally relied on brute-force measurement and processing of pixels arranged on regular grids. In contrast, the human visual system performs significant data reduction from the large number of…
With the rapid advancement of artificial intelligence and deep learning, medical image analysis has become a critical tool in modern healthcare, significantly improving diagnostic accuracy and efficiency. However, AI-based methods also…
Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…
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…
Differential privacy comes equipped with multiple analytical tools for the design of private data analyses. One important tool is the so-called "privacy amplification by subsampling" principle, which ensures that a differentially private…
Online media data, in the forms of images and videos, are becoming mainstream communication channels. However, recent advances in deep learning, particularly deep generative models, open the doors for producing perceptually convincing…
Preserving privacy of continuous and/or high-dimensional data such as images, videos and audios, can be challenging with syntactic anonymization methods which are designed for discrete attributes. Differential privacy, which provides a more…
Have you ever taken a picture only to find out that an unimportant background object ended up being overly salient? Or one of those team sports photos where your favorite player blends with the rest? Wouldn't it be nice if you could tweak…
A basic problem in the design of privacy-preserving algorithms is the private maximization problem: the goal is to pick an item from a universe that (approximately) maximizes a data-dependent function, all under the constraint of…
This paper describes a new model which generates images in novel poses e.g. by altering face expression and orientation, from just a few instances of a human subject. Unlike previous approaches which require large datasets of a specific…
Recently, how to achieve precise image editing has attracted increasing attention, especially given the remarkable success of text-to-image generation models. To unify various spatial-aware image editing abilities into one framework, we…