Utility Metrics for Differential Privacy: No One-Size-Fits-All

In previous posts we discussed different ways to implement differential privacy, each of which offers some trade-off between privacy and utility. But what does “utility” mean, and how do we know we are preserving it? To discuss this topic, we are delighted to introduce another guest author in our blog series, Claire McKay Bowen, Lead Data Scientist for Privacy and Data Security at the Urban Institute. Claire’s research focuses on assessing the quality of differentially private data synthesis methods and science communication. In 2021, the Committee of Presidents of Statistical Societies