US 12,443,750 B2
Context-based entropy management
Jonathan Thomas Burns, Annapolis, MD (US)
Assigned to Twilio Inc., San Francisco, CA (US)
Filed by TWILIO INC., San Francisco, CA (US)
Filed on Jul. 5, 2022, as Appl. No. 17/857,544.
Prior Publication US 2024/0020414 A1, Jan. 18, 2024
Int. Cl. G06F 21/62 (2013.01); G06F 21/60 (2013.01)
CPC G06F 21/6254 (2013.01) [G06F 21/602 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving, via at least one computing device associated with a contextual privacy system of an organization, a request of a user for a data variable associated with at least one entity of a plurality of entities;
determining, via the at least one computing device associated with the contextual privacy system, that data variable is one of a plurality of data variables that contain privacy-sensitive information related to the plurality of entities and are stored in one or more data stores of the organization;
causing, via the at least one computing device associated with the contextual privacy system, the requested data variable to be de-identified based on one or more rules of the contextual privacy system, wherein causing the requested data variable to be de-identified comprises:
obtaining, via the at least one computing device associated with the contextual privacy system, contextual data associated with at least one of: the data variable and the at least one entity;
determining, via the at least one computing device associated with the contextual privacy system, a particular probabilistic model of a plurality of probabilistic models based on the contextual data; and
generating, via the at least one computing device associated with the contextual privacy system, a perturbation value by applying the particular probabilistic model using a particular key as input to the particular probabilistic model; and
in response to the request of the user for the data variable, sending, via the at least one computing device associated with the contextual privacy system, a de-identified value to a computing device of the user by modifying a current value of the data variable by the perturbation value.