Learning with differential privacy for training data
An open source library that makes it easier not only for developers to train machine-learning models with privacy, but also for researchers to advance the state of the art in machine learning with strong privacy guarantees.
3 months ago
Introducing TensorFlow Privacy: Learning with Differential Privacy for Training Data
Posted by Carey Radebaugh (Product Manager) and Ulfar Erlingsson (Research Scientist) Today, we're excited to announce TensorFlow Privacy ( GitHub), an open source library that makes it easier not only for developers to train machine-learning models with privacy, but also for researchers to advance the state of the art in machine learning with strong privacy guarantees.
Google introduces TensorFlow Privacy, a machine learning library with 'strong privacy guarantees'
Google today announced TensorFlow Privacy, a library for its TensorFlow machine learning framework intended to make it easier for developers to train AI models with strong privacy guarantees. It's available in open source, and requires "no expertise in privacy" or underlying mathematics, Google says.
Google is making it easier for AI developers to keep users' data private
Google has announced a new module for its open-source machine learning framework named TensorFlow Privacy. This allows AI developers to use the statistical technique known as differential privacy to safeguard users' data with just a few extra lines of code.
Would you recommend TensorFlow Privacy to a friend?
Launched on the same day Zuck introduces his
"Privacy-Focused Vision for Social Networking"
3 months ago