US 11,893,520 B2
Privacy and proprietary-information preserving collaborative multi-party machine learning
Gabriel Mauricio Silberman, Austin, TX (US); Alain Charles Briancon, Germantown, MD (US); Lee David Harper, Austin, TX (US); Luke Philip Reding, Washington, DC (US); David Alexander Curry, Austin, TX (US); Jean Joseph Belanger, Austin, TX (US); Michael Thomas Wegan, East Lansing, MI (US); and Thejas Narayana Prasad, Spring, TX (US)
Assigned to Cerebri AI Inc., Austin, TX (US)
Filed by Cerebri AI Inc., Austin, TX (US)
Filed on Jun. 7, 2022, as Appl. No. 17/834,756.
Application 17/834,756 is a continuation of application No. 16/151,136, filed on Oct. 3, 2018, granted, now 11,386,295.
Claims priority of provisional application 62/714,252, filed on Aug. 3, 2018.
Prior Publication US 2023/0080773 A1, Mar. 16, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/16 (2006.01); G06Q 10/063 (2023.01); G06F 21/62 (2013.01); G06N 20/00 (2019.01); G06F 18/214 (2023.01)
CPC G06Q 10/063 (2013.01) [G06F 18/2148 (2023.01); G06F 21/6218 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, with one or more processors, a first trained machine learning model accessible to a first entity, wherein:
the first machine learning model is trained on a first training set that includes data the first entity is not permitted to provide to a second entity,
the first trained machine learning model is configured to output tokens, and
the tokens do not reveal more than a threshold amount of information about the data the first entity is not permitted to provide to the second entity;
receiving, with one or more processors, a first set of input features with the first trained machine learning model and, in response, outputting a first token; and
causing, with one or more processors, the first token and a first value associated with the first token to be input into a second trained machine learning model accessible to the second entity, wherein the first value associated with the first token is a token-context value corresponding to the first token, and wherein at least some of the a first set of input features are not provided to the second trained machine learning model.