	US 12,190,211 B2
	Privacy enhanced machine learning
Sebastian Tschiatschek, Cambridge (GB); Olga Ohrimenko, Cambridge (GB); and Shruti Shrikant Tople, Cambridge (GB)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 31, 2022, as Appl. No. 17/829,327.
Application 17/829,327 is a continuation of application No. 16/687,095, filed on Nov. 18, 2019, granted, now 11,366,980.
Claims priority of application No. 1913601 (GB), filed on Sep. 20, 2019.
Prior Publication US 2022/0343111 A1, Oct. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06F 18/21 (2023.01); G06F 18/2115 (2023.01); G06F 18/214 (2023.01); G06F 21/62 (2013.01)

CPC G06N 20/00 (2019.01) [G06F 18/2115 (2023.01); G06F 18/2148 (2023.01); G06F 18/2185 (2023.01); G06F 21/6245 (2013.01)]

20 Claims

1. A system comprising:

a processor; and

a memory storing instructions that upon execution by the processor perform operations comprising:

executing a trusted computing environment configured to store a machine learning model and training data;

storing criteria to access the machine learning model, the criteria indicating performance of the machine learning model;

computing a score using the criteria and a characteristic function, the characteristic function being equal to a performance of the machine learning model plus a sum of the performance of the machine learning model for each individual party; and

controlling access to the machine learning model based on the computed score.