DPD-InfoGAN: Differentially Private Distributed InfoGAN

Vaikkunth Mugunthan, Vignesh Gokul, Lalana Kagal, Shlomo Dubnov

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

1 Scopus citations


Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN has no control over the kinds of images it generates. The Information Maximizing GAN (InfoGAN) is a variant of the default GAN that introduces feature-control variables that are automatically learned by the framework, hence providing greater control over the different kinds of images produced. Due to the high model complexity of InfoGAN, the generative distribution tends to be concentrated around the training data points. This is a critical problem as the models may inadvertently expose the sensitive and private information present in the dataset. To address this problem, we propose a differentially private version of InfoGAN (DP-InfoGAN). We also extend our framework to a distributed setting (DPD-InfoGAN) to allow clients to learn different attributes present in other clients' datasets in a privacy-preserving manner. In our experiments, we show that both DP-InfoGAN and DPD-InfoGAN can synthesize high-quality images with flexible control over image attributes while preserving privacy.

Original languageEnglish
Title of host publicationProceedings of the 1st Workshop on Machine Learning and Systems, EuroMLSys 2021
PublisherAssociation for Computing Machinery, Inc
Number of pages6
ISBN (Electronic)9781450382984
StatePublished - 26 Apr 2021
Externally publishedYes
Event1st Workshop on Machine Learning and Systems, EuroMLSys 2021 - Virtual, Online, United Kingdom
Duration: 26 Apr 2021 → …

Publication series

NameProceedings of the 1st Workshop on Machine Learning and Systems, EuroMLSys 2021


Conference1st Workshop on Machine Learning and Systems, EuroMLSys 2021
Country/TerritoryUnited Kingdom
CityVirtual, Online
Period26/04/21 → …


  • Deep Learning
  • Differential Privacy
  • Distributed Learning
  • InfoGAN

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Human-Computer Interaction
  • Information Systems
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software


Dive into the research topics of 'DPD-InfoGAN: Differentially Private Distributed InfoGAN'. Together they form a unique fingerprint.

Cite this