US Patent Issued to THE TRUSTEES OF PRINCETON UNIVERSITY on Aug. 26 for "System and method for secure and robust distributed deep learning" (New Jersey Inventors)

ALEXANDRIA, Va., Aug. 26 -- United States Patent no. 12,400,031, issued on Aug. 26, was assigned to THE TRUSTEES OF PRINCETON UNIVERSITY (Princeton, N.J.).

"System and method for secure and robust distributed deep learning" was invented by Sanjeev Arora (Princeton, N.J.), Kai Li (Princeton, N.J.), Yangsibo Huang (Princeton, N.J.), Zhao Song (Princeton, N.J.) and Danqi Chen (Princeton, N.J.).

According to the abstract* released by the U.S. Patent & Trademark Office: "According to various embodiments, a method for encrypting image data for a neural network are disclosed. The method includes mixing the image data with other datapoints to form mixed data; and applying a pixel-wise random mask to the mixed data to form encrypted data. Accordin...