DP-CGAN: Differentially Private Synthetic Data and Label Generation
arXiv:2001.09700
Abstract
Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original sensitive datasets because they are not publicly accessible. One of the main challenges in this area is to preserve the privacy of individuals who participate in the training of the GAN models. To address this challenge, we introduce a Differentially Private Conditional GAN (DP-CGAN) training framework based on a new clipping and perturbation strategy, which improves the performance of the model while preserving privacy of the training dataset. DP-CGAN generates both synthetic data and corresponding labels and leverages the recently introduced Renyi differential privacy accountant to track the spent privacy budget. The experimental results show that DP-CGAN can generate visually and empirically promising results on the MNIST dataset with a single-digit epsilon parameter in differential privacy.
7 pages, 4 figures
References in corpus (8)
- Conditional Generative Adversarial Nets
- Deep Learning with Differential Privacy
- Understanding deep learning requires rethinking generalization
- Differentially Private Generative Adversarial Network
- Generating and designing DNA with deep generative models
- Differentially Private Data Generative Models
- LOGAN: Membership Inference Attacks Against Generative Models
- Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data