Since it was introduced in 2006, differential privacy (DP) has become accepted as a gold standard for ensuring that individual-level information is not leaked through statistical analyses or machine learning on sensitive datasets. OpenDP comes at a time when computation and methodological advances, together with a growing need to analyze sensitive data while protecting privacy, are moving DP from theory to practice. In fact, in recent years, DP has seen large-scale deployments by Google, Apple, Microsoft, and the US Census Bureau, all organizations with the resources and expertise to implement their own custom DP systems. What does OpenDP add? OpenDP brings together an open-source community that can contribute to and ensure the trustworthiness of a DP library and an accompanying suite of tools to generate DP statistical releases. This talk describes our efforts to develop the initial OpenDP components and build its community.

This talks is part of the Machine Learning in Science & Engineering  (MLSE) 2020 conference.