# An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors

arXiv: https://arxiv.org/abs/1807.00736 · HTML: https://mlsanity.com/paper/1807.00736/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2018.

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

- [Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation](https://mlsanity.com/paper/2304.01541/) (2023)
- [A Survey of Secure Computation Using Trusted Execution Environments](https://mlsanity.com/paper/2302.12150/) (2023)
- [OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification](https://mlsanity.com/paper/2202.07165/) (2022)
- [Mitigating Leakage from Data Dependent Communications in Decentralized Computing using Differential Privacy](https://mlsanity.com/paper/2112.12411/) (2021)
- [Hawk: Accurate and Fast Privacy-Preserving Machine Learning Using Secure Lookup Table Computation](https://mlsanity.com/paper/2403.17296/) (2024)

## Abstract (arXiv)

Differential privacy has emerged as the main definition for private data analysis and machine learning. The em global model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees and introduces small errors in the output. In contrast, applications of differential privacy in commercial systems by Apple, Google, and Microsoft, use the em local model. Here, users do not trust the data collector, and hence randomize their data before sending it to the data collector. Unfortunately, local model is too strong for several important applications and hence is limited in its applicability. In this work, we propose a framework based on trusted processors and a new definition of differential privacy called em Oblivious Differential Privacy, which combines the best of both local and global models. The algorithms we design in this framework show interesting interplay of ideas from the streaming algorithms, oblivious algorithms, and differential privacy.