US Patent Issued to Ecole Polytechnique Federale De Lausanne (EPFL) on Dec. 2 for "System and method for privacy-preserving distributed training of neural network models on distributed datasets" (Swiss Inventors)

ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,141, issued on Dec. 2, was assigned to Ecole Polytechnique Federale De Lausanne (EPFL) (Lausanne, Switzerland).

"System and method for privacy-preserving distributed training of neural network models on distributed datasets" was invented by Sinem Sav (Lausanne, Switzerland), Juan Ramon Troncoso-Pastoriza (Lausanne, Switzerland), Apostolos Pyrgelis (Bretigny-sur-Morrens, Switzerland), David Froelicher (Lausanne, Switzerland), Joao Gomes De Sa E Sousa (Renens, Switzerland), Jean-Philippe Bossuat (Lausanne, Switzerland) and Jean-Pierre Hubaux (ST-Sulpice, Switzerland).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method and a dist...