US Patent Issued to Enveil on Sept. 15 for "Machine learning training with enforced differential privacy using secure multi-party computation" (Maryland, Virginia Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,495, issued on Sept. 15, was assigned to Enveil Inc. (Fulton, Md.).

"Machine learning training with enforced differential privacy using secure multi-party computation" was invented by Ryan Carr (Fulton, Md.), Jeffery Hein (Glen Burnie, Md.), Guillermo Gutierrez (McLean, Va.), Lauren Procz (Crofton, Md.), Claire Tomesch (Baltimore) and Yizhou Li (McLean, Va.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems for training machine learning models with enforced differential privacy using Secure Multi-Party Computation (SMPC) protocols are disclosed. A method for generating random bits for a Secure Multi-Party Computation (SMPC) protocol...