DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
Differentially private synthetic data is a promising alternative for sensitive data release. Many differentially private generative models have been proposed in the literature. Unfortunately, they all suffer from the low utility of the synthetic data, especially for high resolution images. Here, we propose DPAF, an effective differentially private generative model for high-dimensional image synthesis. Unlike previous methods, which add Gaussian noise in the \textit{backward} phase during model training, DPAF adds differentially private feature aggregation in the \textit{forward} phase, which brings advantages such as reducing information loss in gradient clipping and low sensitivity to aggregation. Since an inappropriate batch size has a negative impact on the utility of synthetic data, DPAF also addresses the problem of setting an appropriate batch size by proposing a novel training strategy that asymmetrically trains different parts of the discriminator. We extensively evaluate different methods on multiple image datasets (up to images of $128\times 128$ resolution) to demonstrate the performance of DPAF.
BibTeX
@article{lin2025dpaf,
author = {Chih-Hsun Lin and Chia-Yi Hsu and Chia-Mu Yu and YANG CAO and Chun-Ying Huang},
title = {{DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase}},
journal = {IEEE Internet of Things Journal},
year = {2025},
doi = {10.1109/jiot.2024.3496920},
}Loading related content...