paper-with-me

Papers

PAC Privacy Preserving Diffusion Models

2023-12-02 · Qipan Xu, Youlong Ding, Xinxi Zhang, Jie Gao, Hao Wang

Data privacy protection is garnering increased attention among researchers. Diffusion models (DMs), particularly with strict differential privacy, can potentially produce images with both high privacy and visual quality. However, challenges arise such as in ensuring robust protection in privatizing specific data attributes, areas where current models often fall short. To address these challenges, we introduce the PAC Privacy Preserving Diffusion Model, a model leverages diffusion principles and ensure Probably Approximately Correct (PAC) privacy. We enhance privacy protection by integrating a private classifier guidance into the Langevin Sampling Process. Additionally, recognizing the gap in measuring the privacy of models, we have developed a novel metric to gauge privacy levels. Our model, assessed with this new metric and supported by Gaussian matrix computations for the PAC bound, has shown superior performance in privacy protection over existing leading private generative models according to benchmark tests.

📄 PDF Abstract BibTeX arXiv:2312.01201

Code (0)

등록된 구현이 없습니다.

Tasks

Privacy Preserving

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Privacy-Preserving Diffusion Model Using Homomorphic Encryption

2024-03-09 · Yaojian Chen, Qiben Yan

In this paper, we introduce a privacy-preserving stable diffusion framework leveraging homomorphic encryption, called HE-Diffusion, which primarily focuses on protecting the denoising phase of the diffusion process. HE-D…

DenoisingImage GenerationmodelPrivacy Preserving

Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation

2024-12-20 · Timur Sattarov, Marco Schreyer, Damian Borth

The increasing demand for privacy-preserving data analytics in finance necessitates solutions for synthetic data generation that rigorously uphold privacy standards. We introduce DP-Fed-FinDiff framework, a novel integra…

DenoisingFederated LearningPrivacy PreservingSynthetic Data Generation+1

Quantifying and Mitigating Privacy Risks for Tabular Generative Models

2024-03-12 · Chaoyi Zhu, Jiayi Tang, Hans Brouwer, Juan F. Pérez 외

Synthetic data from generative models emerges as the privacy-preserving data-sharing solution. Such a synthetic data set shall resemble the original data without revealing identifiable private information. The backbone t…

Privacy Preserving

Privacy Preserving Diffusion Models for Mixed-Type Tabular Data Generation

2025-11-29 · Timur Sattarov, Marco Schreyer, Damian Borth arxiv

We introduce DP-FinDiff, a differentially private diffusion framework for synthesizing mixed-type tabular data. DP-FinDiff employs embedding-based representations for categorical features, reducing encoding overhead and …

Tabular Data Generation

diffGHOST: Diffusion based Generative Hedged Oblivious Synthetic Trajectories

2026-05-11 · Florent Guépin, Cheick Tidiani Cisse, Denis Renaud, François Bidet 외 arxiv

Trajectories are nowadays valuable information for a wide range of applications. However they are also inherently sensitive, as they contain highly personal information about individuals. Facing this challenge, synthesiz…