ALEXANDRIA, Va., Sept. 17 -- United States Patent no. 12,418,412, issued on Sept. 16, was assigned to THE GOVERNING COUNCIL OF THE UNIVERSITY OF TORONTO (Toronto) and Hitachi Solutions Ltd. (Tokyo).

"Secure and robust federated learning system and method by multi-party homomorphic encryption" was invented by Ashish Khisti (Ontario, Canada), Seyederfan Hosseini (Ontario, Canada), Mitsuharu Oba (Tokyo) and Takushi Fujimoto (Tokyo).

According to the abstract* released by the U.S. Patent & Trademark Office: "It is provided a federated learning system for aggregating gradient information representing a result of training an AI model in an edge device, the federated learning system comprising the edge device and a server apparatus, the training...