US 11,989,634 B2
Private federated learning with protection against reconstruction
Abhishek Bhowmick, Santa Clara, CA (US); John Duchi, Menlo Park, CA (US); Julien Freudiger, San Francisco, CA (US); Gaurav Kapoor, Santa Clara, CA (US); and Ryan M. Rogers, Sunnyvale, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Jan. 17, 2020, as Appl. No. 16/501,132.
Claims priority of provisional application 62/774,227, filed on Dec. 1, 2018.
Claims priority of provisional application 62/774,126, filed on Nov. 30, 2018.
Prior Publication US 2021/0166157 A1, Jun. 3, 2021
Int. Cl. G06F 17/00 (2019.01); G06N 3/04 (2023.01); G06N 5/04 (2023.01); G06N 20/20 (2019.01)
CPC G06N 20/20 (2019.01) [G06N 3/04 (2013.01); G06N 5/04 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A non-transitory machine-readable medium storing instructions to cause one or more processors of a data processing system to perform operations comprising:
receiving a machine learning model from a server at a client device;
training the machine learning model using local data at the client device to generate a trained machine learning model;
determining a weight vector that is a difference between first weights of the machine learning model and second weights of the trained machine learning model;
generating an update for the machine learning model, the update including the weight vector;
privatizing the update for the machine learning model by separately privatizing a magnitude and a unit vector of the update; and
transmitting the privatized update for the machine learning model to the server.