Building differentially private machine learning models using TensorFlow

Description

In recent years, the world has become increasingly data driven, and individuals and organizations have developed a stronger awareness and concern for the privacy of their sensitive data. It’s been shown that it’s impossible to disclose statistical results about a private database without revealing some information. Following research on the privacy of sensitive databases, a number of big players such as Google, Apple, and Uber have turned to differential privacy to help guarantee the privacy of sensitive data. That attention from major technology firms has helped bring differential privacy out of research labs and into the realm of software engineering and product development. Differential privacy is now something that smaller firms and software startups are adopting and finding great value in.

Apart from privacy guarantees, advances in differential privacy also allow businesses to unlock more capabilities and increase data utility. One of these capabilities includes the ability to transfer knowledge from existing data through differentially private ensemble models without data privacy concerns. As differential privacy garners recognition in large tech companies, efforts to make current state-of-the-art research more accessible to the general public and small startups are underway. As a contribution to the broader community, Georgian Partners has provided its differential privacy library to the TensorFlow community, making differentially private stochastic gradient descent available in a user-friendly and easy-to-use API that allows users to train private logistic regression and support vector machines.

Chang Liu and Ji Chao Zhang examine differential privacy and its use cases, the new component of the TensorFlow Privacy library, and real-world scenarios along with demonstrations for how to apply the tools.