ALEXANDRIA, Va., June 9 -- United States Patent no. 12,651,167, issued on June 9, was assigned to NEC Corp. (Tokyo).
"Privacy preservation in neural networks" was invented by Roberto Gonzalez Sanchez (Heidelberg, Germany), Vittorio Prodomo (Leganes, Spain) and Marco Gramaglia (Leganes, Germany).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method for privacy preservation for machine learning networks includes splitting a trained neural network into a first part and a second part. The first part is a privacy preservation (PP) encoder and the second part is a PP machine learning (ML) model. The method further includes retraining the PP encoder and the PP ML model. The method can improve artificial intelligen...