Noise generation for differential privacy

A computing apparatus, the computing apparatus comprising:

• a processor;
• and
• a memory storing instructions that, when executed by the processor, configure the apparatus to:
• access a metric value of a metric of each user from a group of users of an application, the metric indicating a measure of an operation of the application by a corresponding user;
• generate a plurality of noise values, each noise value comprising a random value within a noise range, the noise range comprising a range of the metric values from the group of users;
• define a distribution of the plurality of noise values to the group of users;
• modify the metric value of the metric of each user with a corresponding noise value from the plurality of noise values based on the distribution;
• receive, from a client device, a query related to an aggregate metric of the group of users;
• perform, in response to the query, an operation on the modified metric values of the metric of the group of users;
• and
• provide, to the client device, a response based on a result of the operation.

A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to perform operations comprising:

• access a metric value of a metric of each user from a group of users of an application, the metric indicating a measure of an operation of the application by a corresponding user;
• generate a plurality of noise values, each noise value comprising a random value within a noise range, the noise range comprising a range of the metric values from the group of users;
• define a distribution of the plurality of noise values to the group of users;
• modify the metric value of the metric of each user with a corresponding noise value from the plurality of noise values based on the distribution;
• receive, from a client device, a query related to an aggregate metric of the group of users;
• perform, in response to the query, an operation on the modified metric values of the metric of the group of users;
• and
• provide, to the client device, a response based on a result of the operation.