Private Generative Model

Private generative models aim to create synthetic data that preserves the statistical properties of original datasets while safeguarding sensitive information. Current research focuses on enhancing the quality of generated data while maintaining strong privacy guarantees, often employing techniques like differential privacy and secure multi-party computation within various architectures including diffusion models, variational autoencoders, and GANs. This field is crucial for addressing ethical and legal concerns surrounding data usage in machine learning, enabling responsible data sharing and the development of AI systems that respect individual privacy.

Papers

September 27, 2024

Secure Multiparty Generative AI
Manil Shrestha, Yashodha Ravichandran, Edward Kim
Generative Artificial Intelligence Generative AI Model Centralized Machine Learning AI Service Private Generative Model

August 27, 2024

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
Bochao Liu, Pengju Wang, Shiming Ge
LeArning Abstract Differential Privacy Unseen Data Private Generative Model Domain Diffusion

August 8, 2024

Unveiling Hidden Visual Information: A Reconstruction Attack Against Adversarial Visual Information Hiding
Jonggyu Jang, Hyeonsu Lyu, Seongjin Hwang, Hyun Jong Yang
Reconstruction Attack Image Encryption Unveiling Camouflaged Object Private Generative Model Adversarial Watermarking Learnable Image Encryption

June 24, 2024

Toward Fairer Face Recognition Datasets
Alexandre Fournier-Montgieux, Michael Soumm, Adrian Popescu, Bertrand Luvison, Hervé Le Borgne
Face Recognition Facial Data Efficient Verification Private Generative Model

March 14, 2024

Shake to Leak: Fine-tuning Diffusion Models Can Amplify the Generative Privacy Risk
Zhangheng Li, Junyuan Hong, Bo Li, Zhangyang Wang
Diffusion Model Membership Inference Attack Privacy Risk Private Generative Model

December 13, 2023

Differentially Private Gradient Flow based on the Sliced Wasserstein Distance for Non-Parametric Generative Modeling
Ilana Sebag, Muni Sreenivas PYDI, Jean-Yves Franceschi, Alain Rakotomamonjy, Mike Gartrell, Jamal Atif, Alexandre Allauzen
Generative Modeling Gradient Flow Private Stochastic Gradient Descent Private Gradient Sliced Wasserstein Distance Private Generative Model Non Parametric Generative

December 2, 2023

PAC Privacy Preserving Diffusion Models
Qipan Xu, Youlong Ding, Xinxi Zhang, Jie Gao, Hao Wang
Diffusion Model Differential Privacy Privacy Protection Private Generative Model

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

September 28, 2023

Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
Lea Demelius, Roman Kern, Andreas Trügler
Differential Privacy Comprehensive Survey Recent Advance Privacy Guarantee Privacy Utility Private Model Private Generative Model

September 27, 2023

A Unified View of Differentially Private Deep Generative Modeling
Dingfan Chen, Raouf Kerkouche, Mario Fritz
Privacy Preserving Unified View Private Generative Model Privacy Preserving Learning Private Data Generation

July 1, 2023

When Synthetic Data Met Regulation
Georgi Ganev
Synthetic Data Regulatory Compliance PAPER Demand \Cite{meir2021market Private Generative Model Anonymised Data

May 18, 2023

April 20, 2023

DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase
Chih-Hsun Lin, Chia-Yi Hsu, Chia-Mu Yu, Yang Cao, Chun-Ying Huang
Synthetic Data Image Synthesis Private Stochastic Gradient Descent High Resolution Image Synthesis Civil Engineering Phase Private Aggregation Private Generative Model

November 28, 2022

On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation
Yucong Liu, Chi-Hua Wang, Guang Cheng
Neural Topic Privacy Utility Privacy Analysis Privacy Constraint Private Generative Model Private Synthetic Data Generation

November 7, 2022

Private Set Generation with Discriminative Information
Dingfan Chen, Raouf Kerkouche, Mario Fritz
High Dimensional Privacy Issue Renewable Generation Discriminative Information Private Generative Model Private Data Generation

August 5, 2022

DP$^2$-VAE: Differentially Private Pre-trained Variational Autoencoders
Dihong Jiang, Guojun Zhang, Mahdi Karami, Xi Chen, Yunfeng Shao, Yaoliang Yu
Variational Autoencoders Private Data Lung VAE Private Generative Model Text Privatization Private Variational

May 31, 2022

Generative Models with Information-Theoretic Protection Against Membership Inference Attacks
Parisa Hassanzadeh, Robert E. Tillman
Generative Model Generative Adversarial Network Membership Inference Attack Private Generative Model

May 28, 2022

MC-GEN:Multi-level Clustering for Private Synthetic Data Generation
Mingchen Li, Di Zhuang, J. Morris Chang
Synthetic Data Differential Privacy Guarantee Private Synthetic Data Generation Private Generative Model

February 11, 2022

Privacy-preserving Generative Framework Against Membership Inference Attacks
Ruikang Yang, Jianfeng Ma, Yinbin Miao, Xindi Ma
Variational Autoencoder Membership Inference Attack Generative Framework Latent Code Private Generative Model