Differential privacy is a popular privacy-enhancing technology that has been deployed both by industry and government agencies. Unfortunately, existing explanations of differential privacy fail to set accurate privacy expectations for data subjects, which depend on the choice of deployment model. We design and evaluate new explanations of differential privacy for the local and central models, drawing inspiration from prior work explaining other privacy-enhancing technologies such as encryption. We reflect on the challenges in evaluating explanations and on the tradeoffs between qualitative and quantitative evaluation strategies. These reflections offer guidance for other researchers seeking to design and evaluate explanations of privacy-enhancing technologies.

Differential privacy is one of the most popular technologies in the growing area of privacy-conscious data analytics. But differential privacy, along with other privacy-enhancing technologies, may enable privacy theater. In implementations of differential privacy, certain algorithm parameters control the tradeoff between privacy protection for individuals and utility for the data collector; thus, data collectors who do not provide transparency into these parameters may obscure the limited protection offered by their implementation. Through large-scale online surveys, we investigate whether explanations of differential privacy that hide important information about algorithm parameters persuade users to share more browser history data. Surprisingly, we find that the explanations have little effect on individuals' willingness to share data. In fact, most people make up their minds about whether to share before they even learn about the privacy protection.

Deleting data from a trained machine learning (ML) model is a critical task in many applications. For example, we may want to remove the influence of training points that might be out of date or outliers. Regulations such as EU’s General Data Protection Regulation also stipulate that individuals can request to have their data deleted. The naive approach to data deletion is to retrain the ML model on the remaining data, but this is too time consuming. In this work, we propose a new approximate deletion method for linear and logistic models whose computational cost is linear in the the feature dimension d and independent of the number of training data n. This is a significant gain over all existing methods, which all have superlinear time dependence on the dimension. We also develop a new feature-injection test to evaluate the thoroughness of data deletion from ML models.