US 11,727,125 B2
Emergent language based data encryption
Alberto Santamaria-Pang, Niskayuna, NY (US); Peter Henry Tu, Niskayuna, NY (US); Naresh Sundaram Iyer, Ballston Spa, NY (US); Varish Mulwad, Niskayuna, NY (US); and Guangliang Zhao, Latham, NY (US)
Assigned to General Electric Company, Schenectady, NY (US)
Filed by GENERAL ELECTRIC COMPANY, Schenectady, NY (US)
Filed on Mar. 31, 2020, as Appl. No. 16/835,683.
Prior Publication US 2021/0303701 A1, Sep. 30, 2021
Int. Cl. G06F 21/60 (2013.01); G06F 40/30 (2020.01); G06F 40/58 (2020.01); G06N 3/045 (2023.01)
CPC G06F 21/602 (2013.01) [G06F 40/30 (2020.01); G06F 40/58 (2020.01); G06N 3/045 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A system for secure communication, comprising:
a trained agent to acquire a symbol comprising a representation of input data, convert the symbol into an emergent language expression in an emergent language via processing of a first neural network, and initiate transmission of the emergent language expression over a communications network, wherein the emergent language comprises a language based on and specific to the input data, wherein the first neural network is to generate the emergent language which is a new language that is not in existence that is used to represent the input data, wherein the emergent language is not based on a prime number factorization technique;
a trained machine translator to receive the emergent language expression via the communications network and translate the emergent language expression into the input data via processing of a second neural network.