Evaluating the usability of differential privacy tools with data practitioners

Differential privacy (DP) has become the gold standard in privacy-preserving data analytics, but implementing it in realworld datasets and systems remains challenging.

Research

Abstract

‍
Differential privacy (DP) has become the gold standard inprivacy-preserving data analytics, but implementing it in realworld datasets and systems remains challenging. Recentlydeveloped DP tools aim to make DP implementation easier,but limited research has investigated these DP tools’ usability.Through a usability study with 24 US data practitioners withvarying prior DP knowledge, we evaluated the usability offour Python-based open-source DP tools: DiffPrivLib, Tumult Analytics, PipelineDP, and OpenDP. Our results suggestthat using DP tools in this study may help DP novices better understand DP; that Application Programming Interface(API) design and documentation are vital for successful DPimplementation; and that user satisfaction correlates with howwell participants completed study tasks with these DP tools.We provide evidence-based recommendations to improve DPtools’ usability to broaden DP adoption.

Read paper

other Research articles

View All

Research

Evaluating the usability of differential privacy tools with data practitioners

Differential privacy (DP) has become the gold standard in privacy-preserving data analytics, but implementing it in realworld datasets and systems remains challenging.

Research

Using differential privacy to safely release earnings data on post-secondary grads

When the U.S. Census Bureau needed to release data on the median earnings of post-secondary graduates, one Tumult Lab founder helped the Census Bureau design a new differentially private algorithm.

Research

The question of fairness: our proposal for improved DP algorithms in order to strengthen equity

‍While differential privacy offers robust privacy protection, it applies noise to statistics in a manner that can sometimes unfairly impact certain groups.

Research

Evaluating the usability of differential privacy tools with data practitioners

Differential privacy (DP) has become the gold standard in privacy-preserving data analytics, but implementing it in realworld datasets and systems remains challenging.

Research

Using differential privacy to safely release earnings data on post-secondary grads

When the U.S. Census Bureau needed to release data on the median earnings of post-secondary graduates, one Tumult Lab founder helped the Census Bureau design a new differentially private algorithm.

Research

The question of fairness: our proposal for improved DP algorithms in order to strengthen equity

‍While differential privacy offers robust privacy protection, it applies noise to statistics in a manner that can sometimes unfairly impact certain groups.

Unleash the power and value of your data.

Request a Demo