Guidelines for Implementing and Auditing Differentially Private Systems

Abstract

Differential privacy is an information theoretic constraint on algorithms and code. It provides quantification of privacy leakage and formal privacy guarantees that are currently considered the gold standard in privacy protections. In this paper we provide an initial set of "best practices" for developing differentially private platforms, techniques for unit testing that are specific to differential privacy, guidelines for checking if differential privacy is being applied correctly in an application, and recommendations for parameter settings. The genesis of this paper was an initiative by Facebook and Social Science One to provide social science researchers with programmatic access to a URL-shares dataset. In order to maximize the utility of the data for research while protecting privacy, researchers should access the data through an interactive platform that supports differential privacy. The intention of this paper is to provide guidelines and recommendations that can generally be re-used in a wide variety of systems. For this reason, no specific platforms will be named, except for systems whose details and theory appear in academic papers.

References in corpus (12)

• Deep Learning with Differential Privacy
• Renyi Differential Privacy
• Differential Privacy: An Economic Method for Choosing Epsilon
• An Economic Analysis of Privacy Protection and Statistical Accuracy as Social Choices
• On the `Semantics' of Differential Privacy: A Bayesian Formulation
• Proving Differential Privacy via Probabilistic Couplings
• LightDP: Towards Automating Differential Privacy Proofs
• Proving differential privacy in Hoare logic
• Advanced Probabilistic Couplings for Differential Privacy
• Privacy Odometers and Filters: Pay-as-you-Go Composition
• Identifying Cache-Based Side Channels through Secret-Augmented Abstract Interpretation
• Oracle Efficient Private Non-Convex Optimization

Cited by in corpus (7)

• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
• Dopamine: Differentially Private Federated Learning on Medical Data
• The Complexity of Verifying Boolean Programs as Differentially Private
• PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification
• Differentially Private Histograms under Continual Observation: Streaming Selection into the Unknown
• High-Dimensional Differentially-Private EM Algorithm: Methods and Near-Optimal Statistical Guarantees
• Privacy-Preserving Bandits