On Convex Optimization with Semi-Sensitive Features
We study the differentially private (DP) empirical risk minimization (ERM) problem under
the\emph {semi-sensitive DP} setting where only some features are sensitive. This …
the\emph {semi-sensitive DP} setting where only some features are sensitive. This …
Enhancing Learning with Label Differential Privacy by Vector Approximation
Label differential privacy (DP) is a framework that protects the privacy of labels in training
datasets, while the feature vectors are public. Existing approaches protect the privacy of …
datasets, while the feature vectors are public. Existing approaches protect the privacy of …
Locally Private Estimation with Public Features
We initiate the study of locally differentially private (LDP) learning with public features. We
define semi-feature LDP, where some features are publicly available while the remaining …
define semi-feature LDP, where some features are publicly available while the remaining …
On the Differential Privacy and Interactivity of Privacy Sandbox Reports
The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving
advertising functionalities as part of the effort around limiting third-party cookies. In …
advertising functionalities as part of the effort around limiting third-party cookies. In …