Differential Privacy: A Primer for a Non-Technical Audience

By Alexandra Wood, Micah Altman, A. Bembenek, Mark Bun, Marco Gaboardi, James Honaker, Kobbi Nissim, David O'Brien, Thomas Steinke, Salil P. Vadhan. 2018

228 citations recorded by the source corpus.

Differential privacy is a formal mathematical framework for quantifying and managing privacy risks. It provides provable privacy protection against a wide range of potential attacks, including those currently unforeseen. Differential privacy is primarily studied in the context of the collection, analysis, and release of aggregate statistics. These range from simple statistical estimations, such as averages, to machine learning. Tools for differentially private analysis are now in early stages of implementation and use across a variety of academic, industry, and government settings. Interest in the concept is growing among potential users of the tools, as well as within legal and policy communities, as it holds promise as a potential approach to satisfying legal requirements for privacy protection when handling personal information. In particular, differential privacy may be seen as a technical solution for analyzing and sharing data while protecting the privacy of individuals in accordance with existing legal or policy requirements for de-identification or disclosure limitation. This primer seeks to introduce the concept of differential privacy and its privacy implications to non-technical audiences. It provides a simplified and informal, but mathematically accurate, description of differential privacy. Using intuitive illustrations and limited mathematical formalism, it discusses the definition of differential privacy, how differential privacy addresses privacy risks, how differentially private analyses are constructed, and how such analyses can be used in practice. A series of illustrations is used to show how practitioners and policymakers can conceptualize the guarantees provided by differential privacy. These illustrations are also used to explain related concepts, such as composition (the accumulation of risk across multiple analyses), privacy loss parameters, and privacy budgets. This primer aims to provide a foundation that can guide future decisions when analyzing and sharing statistical data about individuals, informing individuals about the privacy protection they will be afforded, and designing policies and regulations for robust privacy protection.

Subfields: Artificial Intelligence, Sociology and Political Science, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

In Safety, Robustness & Interpretability

Citations in the corpus

Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing (2017, background): “Nissim et al. [12] provide a particularly useful primer on understanding differential privacy to a non-76 technical audience as well as the implications of privacy loss in a legal context.”
Differentially-Private "Draw and Discard" Machine Learning (2018, background): “A major struggle in the application of DP to practice [25], [49] is the question of how to keep the overall per-user privacy loss [41], [14] bounded over time.”
Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12 (2017, methodology): “After t days, by composition theorems [9, 15], the privacy loss incurred will be 1 Consider another example: a user opts in to DP, but doesn’t use any emoji for 20 days.”
Proving differential privacy with shadow execution (2019, background): “In this paper, we focus on the verification of algorithms that satisfy pure differential privacy [20], which has several key advantages – it is the strongest one among them, the most popular one, and the easiest to explain to non-technical end-users [36].”
Differentially Private SQL with Bounded User Contribution (2019, methodology): “To represent privacy, there are well-established techniques [19, 28, 29, 38] and perspectives [41] in the literature.”
Algorithms that remember: model inversion attacks and data protection law (2018, background): “A useful lay introduction is provided in [39]”
Machine learning and genomics: precision medicine versus patient privacy (2018, background): “Another formal data protection model, called differential privacy [36, 37], was introduced to address the shortcomings of previous privacy models.”