# PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning

arXiv: https://arxiv.org/abs/2106.04590 · HTML: https://mlsanity.com/paper/2106.04590/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 25 of 25)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [MMD GAN: Towards Deeper Understanding of Moment Matching Network](https://mlsanity.com/paper/1705.08584/) (2017)
- [Subsampled R'enyi Differential Privacy and Analytical Moments Accountant](https://mlsanity.com/paper/1808.00087/) (2018)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Auditing Differentially Private Machine Learning: How Private is Private SGD?](https://mlsanity.com/paper/2006.07709/) (2020)
- [Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning](https://mlsanity.com/paper/2101.04535/) (2021)
- [The Cramer Distance as a Solution to Biased Wasserstein Gradients](https://mlsanity.com/paper/1705.10743/) (2017)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators](https://mlsanity.com/paper/2006.08265/) (2020)
- [DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation](https://mlsanity.com/paper/2002.11603/) (2020)
- [Interpretable Distribution Features with Maximum Testing Power](https://mlsanity.com/paper/1605.06796/) (2016)
- [Fast Two-Sample Testing with Analytic Representations of Probability Measures](https://mlsanity.com/paper/1506.04725/) (2015)
- [Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data](https://mlsanity.com/paper/1901.02477/) (2019)
- [A Characteristic Function Approach to Deep Implicit Generative Modeling](https://mlsanity.com/paper/1909.07425/) (2019)
- [McGan: Mean and Covariance Feature Matching GAN](https://mlsanity.com/paper/1702.08398/) (2017)
- [P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model](https://mlsanity.com/paper/2006.12101/) (2020)
- [Reciprocal Adversarial Learning via Characteristic Functions](https://mlsanity.com/paper/2006.08413/) (2020)
- [Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation](https://mlsanity.com/paper/2006.11204/) (2020)

## Built on by (most cited first, 23 of 23)

- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Differentially Private Diffusion Models Generate Useful Synthetic Images](https://mlsanity.com/paper/2302.13861/) (2023)
- [DP-LDMs: Differentially Private Latent Diffusion Models](https://mlsanity.com/paper/2305.15759/) (2023)
- [Pre-trained Perceptual Features Improve Differentially Private Image Generation](https://mlsanity.com/paper/2205.12900/) (2022)
- [Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generation](https://mlsanity.com/paper/2303.01687/) (2023)
- [PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining](https://mlsanity.com/paper/2311.12850/) (2023)
- [Noise-Aware Statistical Inference with Differentially Private Synthetic Data](https://mlsanity.com/paper/2205.14485/) (2022)
- [On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation](https://mlsanity.com/paper/2211.15809/) (2022)
- [From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis](https://mlsanity.com/paper/2504.01395/) (2025)
- [Tabular Data Synthesis with Differential Privacy: A Survey](https://mlsanity.com/paper/2411.03351/) (2024)
- [Transfer Learning with Pre-trained Conditional Generative Models](https://mlsanity.com/paper/2204.12833/) (2022)
- [A Unified View of Differentially Private Deep Generative Modeling](https://mlsanity.com/paper/2309.15696/) (2023)
- [PFGuard: A Generative Framework with Privacy and Fairness Safeguards](https://mlsanity.com/paper/2410.02246/) (2024)
- [RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models](https://mlsanity.com/paper/2502.12794/) (2025)
- [NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release](https://mlsanity.com/paper/2202.06467/) (2022)
- [Efficient Differentially Private Fine-Tuning of Diffusion Models](https://mlsanity.com/paper/2406.05257/) (2024)
- [A self-attention-based differentially private tabular GAN with high data utility](https://mlsanity.com/paper/2312.13031/) (2023)
- [Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training](https://mlsanity.com/paper/2412.09842/) (2024)
- [DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models](https://mlsanity.com/paper/2508.04208/) (2025)
- [PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning](https://mlsanity.com/paper/2512.07342/) (2025)
- [DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase](https://mlsanity.com/paper/2304.12185/) (2023)
- [VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis](https://mlsanity.com/paper/2503.16195/) (2025)
- [From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum](https://mlsanity.com/paper/2601.06368/) (2026)

## Abstract (arXiv)

We propose a new framework of synthesizing data using deep generative models in a differentially private manner. Within our framework, sensitive data are sanitized with rigorous privacy guarantees in a one-shot fashion, such that training deep generative models is possible without re-using the original data. Hence, no extra privacy costs or model constraints are incurred, in contrast to popular approaches such as Differentially Private Stochastic Gradient Descent (DP-SGD), which, among other issues, causes degradation in privacy guarantees as the training iteration increases. We demonstrate a realization of our framework by making use of the characteristic function and an adversarial re-weighting objective, which are of independent interest as well. Our proposal has theoretical guarantees of performance, and empirical evaluations on multiple datasets show that our approach outperforms other methods at reasonable levels of privacy.