DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion

Dongjie Chen, Sen Ching S. Cheung, Chen Nee Chuah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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 languageEnglish
Title of host publication2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Proceedings
Pages3660-3664
Number of pages5
ISBN (Electronic)9798350302585
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Kuala Lumpur, Malaysia
Duration: Oct 8 2023Oct 11 2023

Publication series

Name2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023 - Proceedings

Conference

Conference2023 IEEE International Conference on Image Processing Challenges and Workshops, ICIPCW 2023
Country/TerritoryMalaysia
CityKuala Lumpur
Period10/8/2310/11/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • differential privacy
  • Gaussian optimized model inversion
  • Generative adversarial networks

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'DPGOMI: Differentially Private Data Publishing with Gaussian Optimized Model Inversion'. Together they form a unique fingerprint.

Cite this