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

Summary:

‍While differential privacy offers robust privacy protection, it applies noise to statistics in a manner that can sometimes unfairly impact certain groups. Using summaries on educational funding and voter benefit distribution from the U.S. Census Bureau, we initiate a first-of-its-kind study into the impact of formally private mechanisms (based on differential privacy) on fair and equitable decision-making. We propose novel measures of fairness in the context of randomized differentially private algorithms and identify a range of causes of outcome disparities. We also explore improved algorithms to remedy the observed unfairness.

‍

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