ALEXANDRIA, Va., Oct. 21 -- United States Patent no. 12,443,850, issued on Oct. 14, was assigned to SAP SE (Walldorf, Germany).
"Trainable differential privacy for machine learning" was invented by Anderson Santana De Oliveira (Antibes, France) and Caelin Kaplan (Nice, France).
According to the abstract* released by the U.S. Patent & Trademark Office: "Technologies are provided for training machine learning models using a differential privacy mechanism. Training data can be transformed using a differential privacy mechanism that comprises a trainable confidence parameter. The transformed training data can be used to generate class predictions using the machine learning model. A class prediction loss can be determined based on differences ...