# DPGen: Automated Program Synthesis for Differential Privacy

arXiv: https://arxiv.org/abs/2109.07441 · HTML: https://mlsanity.com/paper/2109.07441/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2021.

## Built on by (most cited first, 3 of 3)

- [Privacy for Free: How does Dataset Condensation Help Privacy?](https://mlsanity.com/paper/2206.00240/) (2022)
- [PPA: Preference Profiling Attack Against Federated Learning](https://mlsanity.com/paper/2202.04856/) (2022)
- [Robust Representation Learning for Privacy-Preserving Machine Learning: A Multi-Objective Autoencoder Approach](https://mlsanity.com/paper/2309.04427/) (2023)

## Abstract (arXiv)

Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with a noise-free (non-private) algorithm. The designer then decides where to add noise, and how much of it to add. This can be a non-trivial process -- if not done carefully, the algorithm might either violate differential privacy or have low utility. In this paper, we present DPGen, a program synthesizer that takes in non-private code (without any noise) and automatically synthesizes its differentially private version (with carefully calibrated noise). Under the hood, DPGen uses novel algorithms to automatically generate a sketch program with candidate locations for noise, and then optimize privacy proof and noise scales simultaneously on the sketch program. Moreover, DPGen can synthesize sophisticated mechanisms that adaptively process queries until a specified privacy budget is exhausted. When evaluated on standard benchmarks, DPGen is able to generate differentially private mechanisms that optimize simple utility functions within 120 seconds. It is also powerful enough to synthesize adaptive privacy mechanisms.