# P3GM: Private High-Dimensional Data Release via Privacy Preserving Phased Generative Model

arXiv: https://arxiv.org/abs/2006.12101 · HTML: https://mlsanity.com/paper/2006.12101/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 21 of 21)

- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence](https://mlsanity.com/paper/2111.01177/) (2021)
- [Differentially Private Query Release Through Adaptive Projection](https://mlsanity.com/paper/2103.06641/) (2021)
- [PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning](https://mlsanity.com/paper/2106.04590/) (2021)
- [Generating Private Synthetic Data with Genetic Algorithms](https://mlsanity.com/paper/2306.03257/) (2023)
- [Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility](https://mlsanity.com/paper/2305.10994/) (2023)
- [Tabular Data Synthesis with Differential Privacy: A Survey](https://mlsanity.com/paper/2411.03351/) (2024)
- [Privacy Auditing Synthetic Data Release through Local Likelihood Attacks](https://mlsanity.com/paper/2508.21146/) (2025)
- [Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions](https://mlsanity.com/paper/2209.04022/) (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)
- [NeuroMixGDP: A Neural Collapse-Inspired Random Mixup for Private Data Release](https://mlsanity.com/paper/2202.06467/) (2022)
- [Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation](https://mlsanity.com/paper/2408.14738/) (2024)
- [Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training](https://mlsanity.com/paper/2410.19941/) (2024)
- [Enabling Trade-offs in Privacy and Utility in Genomic Data Beacons and Summary Statistics](https://mlsanity.com/paper/2302.01763/) (2023)
- [PAC Privacy Preserving Diffusion Models](https://mlsanity.com/paper/2312.01201/) (2023)
- [DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks](https://mlsanity.com/paper/2508.21340/) (2025)
- [Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective](https://mlsanity.com/paper/2601.22434/) (2026)
- [DPAF: Image Synthesis via Differentially Private Aggregation in Forward Phase](https://mlsanity.com/paper/2304.12185/) (2023)
- [Private Gradient Estimation is Useful for Generative Modeling](https://mlsanity.com/paper/2305.10662/) (2023)
- [Privacy-Preserving Model Transcription with Differentially Private Synthetic Distillation](https://mlsanity.com/paper/2601.19090/) (2026)

## Abstract (arXiv)

How can we release a massive volume of sensitive data while mitigating privacy risks? Privacy-preserving data synthesis enables the data holder to outsource analytical tasks to an untrusted third party. The state-of-the-art approach for this problem is to build a generative model under differential privacy, which offers a rigorous privacy guarantee. However, the existing method cannot adequately handle high dimensional data. In particular, when the input dataset contains a large number of features, the existing techniques require injecting a prohibitive amount of noise to satisfy differential privacy, which results in the outsourced data analysis meaningless. To address the above issue, this paper proposes privacy-preserving phased generative model (P3GM), which is a differentially private generative model for releasing such sensitive data. P3GM employs the two-phase learning process to make it robust against the noise, and to increase learning efficiency (e.g., easy to converge). We give theoretical analyses about the learning complexity and privacy loss in P3GM. We further experimentally evaluate our proposed method and demonstrate that P3GM significantly outperforms existing solutions. Compared with the state-of-the-art methods, our generated samples look fewer noises and closer to the original data in terms of data diversity. Besides, in several data mining tasks with synthesized data, our model outperforms the competitors in terms of accuracy.