OpenDP will be a community effort to build a system of tools for enabling privacy-protective analysis of sensitive personal data, focused on an open-source library of algorithms for generating differentially private statistical releases. We aim for this platform to become the standard body of trusted and open-source implementations of differentially private algorithms for statistical analysis and machine learning on sensitive data, and a pathway that rapidly brings the newest algorithmic developments to a wide array of practitioners. We envision OpenDP as an open-source project for the differential privacy community to develop general-purpose, vetted, usable, and scalable tools for differential privacy, which users can simply, robustly and confidently deploy. During the first year, we will run workshops and provide small research grants to build a community of DP experts committed to an open-source library of DP algorithms and a system to deploy them. Together with this community we will produce a blueprint for library contributions and system deployment, and begin this development. This will enable researchers to find, explore and analyze sensitive data, and for government, industry, and other institutions to share such sources. The resulting contributions to knowledge, given the burgeoning new sources of sensitive data, will help shape all fields of knowledge on human behavior.
OpenDP is funded by a grant from the Sloan Foundation
|OpenDP: extract from Sloan Proposal||346 KB|