Training Differentially Private Ad Prediction Models with Semi-Sensitive Features

Understand

Motivated by problems arising in digital advertising, we introduce the task of training differentially private (DP) machine learning models with semi-sensitive features.

• In this setting, a subset of the features is known to the attacker (and thus need not be protected) while the remaining features as well as the label are unknown to the attacker and should be protected by the DP guarantee.
• This task interpolates between training the model with full DP (where the label and all features should be protected) or with label DP (where all the features are considered known, and only the label should be protected).
• We present a new algorithm for training DP models with semi-sensitive features.