# On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation

arXiv: https://arxiv.org/abs/2211.15809 · HTML: https://mlsanity.com/paper/2211.15809/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 51 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 30 of 30)

- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [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)
- [Synthetic Data -- Anonymisation Groundhog Day](https://mlsanity.com/paper/2011.07018/) (2020)
- [Winning the NIST Contest: A scalable and general approach to differentially private synthetic data](https://mlsanity.com/paper/2108.04978/) (2021)
- [Synthesizing Tabular Data using Generative Adversarial Networks](https://mlsanity.com/paper/1811.11264/) (2018)
- [Benchmarking Differentially Private Synthetic Data Generation Algorithms](https://mlsanity.com/paper/2112.09238/) (2021)
- [DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation](https://mlsanity.com/paper/2002.11603/) (2020)
- [Graphical-model based estimation and inference for differential privacy](https://mlsanity.com/paper/1901.09136/) (2019)
- [Synthetic Data -- what, why and how?](https://mlsanity.com/paper/2205.03257/) (2022)
- [G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators](https://mlsanity.com/paper/1906.09338/) (2019)
- [Differentially Private Synthetic Data: Applied Evaluations and Enhancements](https://mlsanity.com/paper/2011.05537/) (2020)
- [Differentially Private Data Generative Models](https://mlsanity.com/paper/1812.02274/) (2018)
- [Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data](https://mlsanity.com/paper/1901.02477/) (2019)
- [PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning](https://mlsanity.com/paper/2106.04590/) (2021)
- [PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions](https://mlsanity.com/paper/1601.03229/) (2016)
- [Generating Synthetic but Plausible Healthcare Record Datasets](https://mlsanity.com/paper/1807.01514/) (2018)
- [dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation](https://mlsanity.com/paper/2207.05810/) (2022)
- [Faking feature importance: A cautionary tale on the use of differentially-private synthetic data](https://mlsanity.com/paper/2203.01363/) (2022)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on GANs?](https://mlsanity.com/paper/2111.13617/) (2021)
- [Visualizing Privacy-Utility Trade-Offs in Differentially Private Data Releases](https://mlsanity.com/paper/2201.05964/) (2022)
- [Relaxed Marginal Consistency for Differentially Private Query Answering](https://mlsanity.com/paper/2109.06153/) (2021)
- [Enabling Synthetic Data adoption in regulated domains](https://mlsanity.com/paper/2204.06297/) (2022)
- [The Privacy-Utility Tradeoff of Robust Local Differential Privacy](https://mlsanity.com/paper/2101.09139/) (2021)

## Built on by (most cited first, 8 of 8)

- [Graphical vs. Deep Generative Models: Measuring the Impact of Differentially Private Mechanisms and Budgets on Utility](https://mlsanity.com/paper/2305.10994/) (2023)
- [Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models](https://mlsanity.com/paper/2406.13012/) (2024)
- [Synthetic Tabular Data: Methods, Attacks and Defenses](https://mlsanity.com/paper/2506.06108/) (2025)
- [FLAIM: AIM-based Synthetic Data Generation in the Federated Setting](https://mlsanity.com/paper/2310.03447/) (2023)
- [Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data](https://mlsanity.com/paper/2406.13130/) (2024)
- [GReaTER: Generate Realistic Tabular data after data Enhancement and Reduction](https://mlsanity.com/paper/2503.15564/) (2025)
- [DEREC-SIMPRO: unlock Language Model benefits to advance Synthesis in Data Clean Room](https://mlsanity.com/paper/2411.00879/) (2024)
- [Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation](https://mlsanity.com/paper/2504.10987/) (2025)

## Abstract (arXiv)

Devising procedures for auditing generative model privacy-utility tradeoff is an important yet unresolved problem in practice. Existing works concentrates on investigating the privacy constraint side effect in terms of utility degradation of the train on synthetic, test on real paradigm of synthetic data training. We push such understanding on privacy-utility tradeoff to next level by observing the privacy deregulation side effect on synthetic training data utility. Surprisingly, we discover the Utility Recovery Incapability of DP-CTGAN and PATE-CTGAN under privacy deregulation, raising concerns on their practical applications. The main message is Privacy Deregulation does NOT always imply Utility Recovery.