Machine Learning at Scale with Differential Privacy in TensorFlow

No ratings

Presented at PEPR'19 2019 by

Nicolas Papernot

This talk will illustrate how learning with rigorous differential privacy guarantees is possible using TensorFlow Privacy, an open-source library that makes it easier not only for developers to train ML models with privacy in real-world systems, but also for researchers to advance the state-of-the-art in ML with strong privacy guarantees.