# Learning Differentially Private Mechanisms

arXiv: https://arxiv.org/abs/2101.00961 · HTML: https://mlsanity.com/paper/2101.00961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 37 references that are in the map.
- First posted on arXiv 4 Jan 2021.

## Builds on (most cited first, 11 of 11)

- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds](https://mlsanity.com/paper/1605.02065/) (2016)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Detecting Violations of Differential Privacy](https://mlsanity.com/paper/1805.10277/) (2018)
- [Understanding the Sparse Vector Technique for Differential Privacy](https://mlsanity.com/paper/1603.01699/) (2016)
- [Towards Practical Differential Privacy for SQL Queries](https://mlsanity.com/paper/1706.09479/) (2017)
- [CheckDP: An Automated and Integrated Approach for Proving Differential Privacy or Finding Precise Counterexamples](https://mlsanity.com/paper/2008.07485/) (2020)
- [Proving Differential Privacy via Probabilistic Couplings](https://mlsanity.com/paper/1601.05047/) (2016)
- [LightDP: Towards Automating Differential Privacy Proofs](https://mlsanity.com/paper/1607.08228/) (2016)
- [Synthesizing Coupling Proofs of Differential Privacy](https://mlsanity.com/paper/1709.05361/) (2017)
- [Proving Differential Privacy with Shadow Execution](https://mlsanity.com/paper/1903.12254/) (2019)

## Abstract (arXiv)

Differential privacy is a formal, mathematical definition of data privacy that has gained traction in academia, industry, and government. The task of correctly constructing differentially private algorithms is non-trivial, and mistakes have been made in foundational algorithms. Currently, there is no automated support for converting an existing, non-private program into a differentially private version. In this paper, we propose a technique for automatically learning an accurate and differentially private version of a given non-private program. We show how to solve this difficult program synthesis problem via a combination of techniques: carefully picking representative example inputs, reducing the problem to continuous optimization, and mapping the results back to symbolic expressions. We demonstrate that our approach is able to learn foundational algorithms from the differential privacy literature and significantly outperforms natural program synthesis baselines.