Private Generative Adversarial Network

Private Generative Adversarial Networks (PGANs) combine the data generation capabilities of GANs with differential privacy mechanisms to create synthetic datasets that preserve user confidentiality. Current research focuses on improving the quality of synthetic data generated by PGANs while maintaining strong privacy guarantees, exploring various architectures like conditional GANs and employing techniques such as model inversion to enhance training stability and data utility. This field is significant for enabling responsible data sharing and analysis in sensitive domains like healthcare and location tracking, where privacy concerns are paramount.

Papers

April 10, 2024

Differentially Private GANs for Generating Synthetic Indoor Location Data
Vahideh Moghtadaiee, Mina Alishahi, Milad Rabiei
Differential Privacy Private Generative Adversarial Network Synthetic Trajectory Data

February 21, 2024

Protect and Extend -- Using GANs for Synthetic Data Generation of Time-Series Medical Records
Navid Ashrafi, Vera Schmitt, Robert P. Spang, Sebastian Möller, Jan-Niklas Voigt-Antons
Generative Adversarial Network Synthetic Data Generation Privacy Preservation Private Generative Adversarial Network

January 9, 2024

Deep Efficient Private Neighbor Generation for Subgraph Federated Learning
Ke Zhang, Lichao Sun, Bolin Ding, Siu Ming Yiu, Carl Yang
Federated Learning Subgraph Structure Local Differential Privacy Local Graph Private Generative Adversarial Network

December 20, 2023

A self-attention-based differentially private tabular GAN with high data utility
Zijian Li, Zhihui Wang
Generative Adversarial Network Differential Privacy Conditional Generative Adversarial Network Data Efficient Private Generative Adversarial Network Private Tabular Data

October 19, 2023

PrivacyGAN: robust generative image privacy
Mariia Zameshina, Marlene Careil, Olivier Teytaud, Laurent Najman
Privacy Preservation Privacy Protection Empirical Privacy Private Generative Model Private Generative Adversarial Network

October 15, 2023

Private Synthetic Data Meets Ensemble Learning
Haoyuan Sun, Navid Azizan, Akash Srivastava, Hao Wang
Synthetic Data Differential Privacy Ensemble Learning Synthetic Dataset Private Generative Adversarial Network

February 22, 2023

Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning
Van-Tuan Tran, Huy-Hieu Pham, Kok-Seng Wong
New Framework C Gan Private Data Personalized Subject Cross Silo Federated Learning Decentralized Deep Learning Private Generative Adversarial Network

February 6, 2023

Private GANs, Revisited
Alex Bie, Gautam Kamath, Guojun Zhang
GAN Training Representation Drift Discriminative Training Private Generative Adversarial Network

June 28, 2022

Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs
Chang Sun, Johan van Soest, Michel Dumontier
Generative Adversarial Network Imbalanced Data Synthetic Medical Data Correlation Graph Ct Gan Private Generative Adversarial Network

January 10, 2022

Differentially Private Generative Adversarial Networks with Model Inversion
Dongjie Chen, Sen-ching Samson Cheung, Chen-Nee Chuah, Sally Ozonoff
Generative Adversarial Network Model Inversion Private Model Private Generative Adversarial Network