Fri. Jul 10th, 2020

Microsoft partners with Harvard University in Open Differential Privacy project

2 min read

Microsoft partnered with Harvard OpenDP Initiative to develop and open source the first platform for differential privacy. This work has lasted for almost a year.

The concept of differential privacy was jointly studied by Cynthia Dwork, Gordon McKay professor of CS at Harvard and Distinguished Scientist at Microsoft, for several years and was proposed in 2006. It can analyze the entire data set without revealing individual privacy information, draw effective conclusions, and prevent differential attacks.

This is mainly achieved via

  • A small amount of statistical “noise” is added to each result to mask the contribution of individual data points. This noise works to protect the privacy of an individual while not significantly impacting the accuracy of the answers extracted by analysts and researchers.
  • The amount of information revealed from each query is calculated and deducted from an overall privacy budget to halt additional queries when personal privacy may be compromised.

The technology is still in the development stage, Microsoft said that the open-source platform is very important for the technology to mature and widely used. “Large and open datasets possess an unimaginable amount of potential. The differential privacy platform paves the way for us to contribute, collaborate and harness this data, and we need your help to grow and analyze the world’s collective data repositories. The resulting insights will have an enormous and lasting impact and will open new avenues of research that allow us to develop creative solutions for some of the most pressing problems we currently face.”

The OpenDP platform is now open source and can be used for testing and building.