October 28–31, 2019
Please log in

TensorFlow Privacy: Learning with differential privacy for training data

Ulfar Erlingsson (Google Brain)
5:00pm5:40pm Wednesday, October 30, 2019
Location: Grand Ballroom E
Average rating: *****
(5.00, 1 rating)

Who is this presentation for?

  • ML practitioners, ML researchers, and decision makers




When evaluating ML models, it can be difficult to tell the difference between what the models learned to generalize from training and what the models have simply memorized. And that difference can be crucial in some ML tasks, such as when ML models are trained using sensitive data. Recently, new techniques have emerged for differentially private training of ML models, including deep neural networks (DNNs), that used modified stochastic gradient descent to provide strong privacy guarantees for training data.

Those techniques are now available, and they’re both practical and can be easy to use. This said, they come with their own set of hyperparameters that need to be tuned, and they necessarily make learning less sensitive to outlier data in ways that are likely to slightly reduce utility. Úlfar Erlingsson explores the basics of ML privacy, introduces differential privacy and why it’s considered a gold standard, explains the concrete use of ML privacy and the principled techniques behind it, and dives into intended and unintended memorization and how it differs from generalization.

Prerequisite knowledge

  • Experience using TensorFlow to train ML models
  • A basic understanding of stochastic gradient descent

What you'll learn

  • Learn what it means to provide privacy guarantees for ML models and how such guarantees can be achieved in practice using TensorFlow Privacy
Photo of Ulfar Erlingsson

Ulfar Erlingsson

Google Brain

Úlfar Erlingsson is a research scientist on the Brain team at Google, working primarily on privacy and security of deep learning systems. Previously, Úlfar led computer security research at Google and was a researcher at Microsoft Research, associate professor at Reykjavik University, cofounder and CTO of the internet security startup GreenBorder Technologies, and director of privacy protection at deCODE genetics. Úlfar holds a PhD in computer science from Cornell University.

  • O'Reilly
  • TensorFlow
  • Google Cloud
  • IBM
  • Databricks
  • Tensor Networks
  • VMware
  • Amazon Web Services
  • One Convergence
  • Quantiphi
  • Lambda Labs
  • Tech Mahindra
  • cnvrg.io
  • Determined AI
  • Inferencery
  • Manceps, Inc.
  • PerceptiLabs
  • Valohai

Contact us


For conference registration information and customer service


For more information on community discounts and trade opportunities with O’Reilly conferences


For information on exhibiting or sponsoring a conference


For media/analyst press inquires