Since the advent of differential privacy, a number of systems supporting differentially private data analyses have been implemented and deployed. This article tracks real-world deployments, production software packages, and research prototypes.
Real-world deployments
Name Organization Year Introduced Notes Still in use? OnTheMap: Interactive tool for exploration of US income and commute patterns. US Census Bureau 2008 First deployment of differential privacy YesRAPPOR in Chrome Browser to collect security metricsGoogle2014First widespread use of local differential privacyNoEmoji analytics; analytics. Improve: QuickType, emoji; Spotlight deep link suggestions; Lookup Hints in Notes. Emoji suggestions, health type usage estimates, Safari energy drain statistics, Autoplay intent detection (also in Safari) Apple 2017 Yes Application telemetry Microsoft 2017 Application usage statistics Microsoft Windows. yes Flex: A SQL-based system developed for internal Uber analytics Uber 2017 Unknown2020 CensusUS Census Bureau 2018 YesAudience Engagement APILinkedIn2020YesLabor Market InsightsLinkedIn2020YesCOVID-19 Community Mobility ReportsGoogle2020UnknownAdvertiser QueriesLinkedIn2020U.S. Broadband Coverage Data SetMicrosoft2021UnknownCollege Scorecard WebsiteIRS and Dept. of Education2021UnknownOhm ConnectRecurve2021Live Birth DatasetIsraeli Ministry of Health2024Yes
Production software packages These software packages purport to be usable in production systems. They are split in two categories: those focused on answering statistical queries with differential privacy, and those focused on training machine learning models with differential privacy.
Statistical analyses
Name Developer Year Introduced Notes Still maintained? Google's differential privacy libraries Google 2019 Building block libraries in Go, C++, and Java; end-to-end framework in Go. YesOpenDPHarvard, Microsoft2020Core library in Rust, SDK in Python with an SQL interface.Yes Tumult Analytics Tumult Labs 2022 Python library, running on Apache Spark. Yes PipelineDP Google, OpenMined 2022 Python library, running on Apache Spark, Apache Beam, or locally. Yes PSI (Ψ): A Private data Sharing Interface Harvard University Privacy Tools Project. 2016 NoTopDown AlgorithmUnited States Census Bureau2020Production code used in the 2020 US Census.No
Machine learning
Name Developer Year Introduced Notes Still maintained?DiffprivlibIBM2019Python library.YesTensorFlow PrivacyGoogle2019Differentially private training in TensorFlow.YesOpacusMeta2020Differentially private training in PyTorch.Yes
Research projects and prototypes Name Citation Year Published Notes PINQ: An API implemented in C#. 2010 Airavat: A MapReduce-based system implemented in Java hardened with SELinux-like access control. 2010 Fuzz: Time-constant implementation in Caml Light of a domain-specific language. 2011 GUPT: Implementation of the sample-and-aggregate framework. 2012KTELO: A framework and system for answering linear counting queries. 2018
See also Differential Privacy Secure multi-party computation
References