# Secure Random Sampling in Differential Privacy

arXiv: https://arxiv.org/abs/2107.10138 · HTML: https://mlsanity.com/paper/2107.10138/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2021.

## Built on by (most cited first, 5 of 5)

- [Differential Privacy: What is all the noise about?](https://mlsanity.com/paper/2205.09453/) (2022)
- [PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction](https://mlsanity.com/paper/2507.00230/) (2025)
- [Prediction with Expert Advice under Local Differential Privacy](https://mlsanity.com/paper/2512.06971/) (2025)
- [One RNG to Rule Them All: How Randomness Becomes an Attack Vector in Machine Learning](https://mlsanity.com/paper/2602.09182/) (2026)
- [Dithered Gaussian Mechanism for Randomness-Efficient Differential Privacy](https://mlsanity.com/paper/2607.06320/) (2026)

## Abstract (arXiv)

Differential privacy is among the most prominent techniques for preserving privacy of sensitive data, oweing to its robust mathematical guarantees and general applicability to a vast array of computations on data, including statistical analysis and machine learning. Previous work demonstrated that concrete implementations of differential privacy mechanisms are vulnerable to statistical attacks. This vulnerability is caused by the approximation of real values to floating point numbers. This paper presents a practical solution to the finite-precision floating point vulnerability, where the inverse transform sampling of the Laplace distribution can itself be inverted, thus enabling an attack where the original value can be retrieved with non-negligible advantage. The proposed solution has the advantages of being generalisable to any infinitely divisible probability distribution, and of simple implementation in modern architectures. Finally, the solution has been designed to make side channel attack infeasible, because of inherently exponential, in the size of the domain, brute force attacks.