# Differentially Private Releasing via Deep Generative Model (Technical Report)

arXiv: https://arxiv.org/abs/1801.01594 · HTML: https://mlsanity.com/paper/1801.01594/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2018.

## Built on by (most cited first, 10 of 10)

- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining](https://mlsanity.com/paper/2311.12850/) (2023)
- [Deep Generative Models, Synthetic Tabular Data, and Differential Privacy: An Overview and Synthesis](https://mlsanity.com/paper/2307.15424/) (2023)
- [Mitigating Statistical Bias within Differentially Private Synthetic Data](https://mlsanity.com/paper/2108.10934/) (2021)
- [Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation](https://mlsanity.com/paper/2409.02404/) (2024)
- [Batch Clipping and Adaptive Layerwise Clipping for Differential Private Stochastic Gradient Descent](https://mlsanity.com/paper/2307.11939/) (2023)
- [A self-attention-based differentially private tabular GAN with high data utility](https://mlsanity.com/paper/2312.13031/) (2023)
- [DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase](https://mlsanity.com/paper/2304.12185/) (2023)
- [Partition-based differentially private synthetic data generation](https://mlsanity.com/paper/2310.06371/) (2023)

## Abstract (arXiv)

Privacy-preserving releasing of complex data (e.g., image, text, audio) represents a long-standing challenge for the data mining research community. Due to rich semantics of the data and lack of a priori knowledge about the analysis task, excessive sanitization is often necessary to ensure privacy, leading to significant loss of the data utility. In this paper, we present dp-GAN, a general private releasing framework for semantic-rich data. Instead of sanitizing and then releasing the data, the data curator publishes a deep generative model which is trained using the original data in a differentially private manner; with the generative model, the analyst is able to produce an unlimited amount of synthetic data for arbitrary analysis tasks. In contrast of alternative solutions, dp-GAN highlights a set of key features: (i) it provides theoretical privacy guarantee via enforcing the differential privacy principle; (ii) it retains desirable utility in the released model, enabling a variety of otherwise impossible analyses; and (iii) most importantly, it achieves practical training scalability and stability by employing multi-fold optimization strategies. Through extensive empirical evaluation on benchmark datasets and analyses, we validate the efficacy of dp-GAN.