2020

The Trade-Offs of Private Prediction

van der Maaten, Laurens, Hannun, Awni

Understand

Machine learning models leak information about their training data every time they reveal a prediction.

  • This is problematic when the training data needs to remain private.
  • Private prediction methods limit how much information about the training data is leaked by each prediction.
  • Private prediction can also be achieved using models that are trained by private training methods.

Reading the bibliography…