Abstract
High-dimensional data are widely used in the era of deep learning with numerous applications. However, certain data which has sensitive information are not allowed to be shared without privacy protection. In this paper, we propose a novel differentially private data releasing method called Differentially Private Data Publishing with Gaussian Optimized Model Inversion (DPGOMI) to address this issue. Our approach involves mapping private data to the latent space using a public generator, followed by a lower-dimensional DP-GAN with better convergence properties. We evaluate the performance of DPGOMI on standard datasets CIFAR10 and SVHN, as well as on a facial landmark dataset for Autism screening. Our results show that DPGOMI outperforms the standard DP-GAN method in terms of Inception Score, Fréchet Inception Distance, and classification performance, while providing the same level of privacy. Our proposed approach offers a promising solution for protecting sensitive data in GAN training while maintaining high-quality results.
Original language | English |
---|---|
Title of host publication | 2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Proceedings |
Pages | 3660-3664 |
Number of pages | 5 |
ISBN (Electronic) | 9798350302585 |
DOIs | |
State | Published - 2023 |
Event | 2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Kuala Lumpur, Malaysia Duration: Oct 8 2023 → Oct 11 2023 |
Publication series
Name | 2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Proceedings |
---|
Conference
Conference | 2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 |
---|---|
Country/Territory | Malaysia |
City | Kuala Lumpur |
Period | 10/8/23 → 10/11/23 |
Bibliographical note
Publisher Copyright:© 2023 IEEE.
Funding
Research reported in this project was supported by the National Institutes of Health, United States of America under award number R01MH121344 and the Child Family Endowed Professorship. This work was supported in part by Oracle Cloud credits and related resources provided by the Oracle for Research program.
Funders | Funder number |
---|---|
Oracle cloud | |
National Institutes of Health (NIH) | R01MH121344 |
National Institutes of Health (NIH) |
Keywords
- differential privacy
- Gaussian optimized model inversion
- Generative adversarial networks
ASJC Scopus subject areas
- Signal Processing
- Media Technology