Differential noise for long-term privacy and short-term privacy preservation

1 . A method of reporting usage of a computing device, the method comprising:

detecting, over a period of time, a plurality of events associated with a function of the computing device;

determining a first noise associated with the plurality of events over the period of time;

adding the first noise and a second noise to a value corresponding to the plurality of events, wherein the second noise is independent of the first noise; and

sending a noisy report identifying a usage of the function to a device usage service, the noisy report including the value with the first noise and the second noise.

2 . The method of claim 1 , further comprising:

receiving a second noise distribution from the device usage service, wherein the second noise is generated based on the second noise distribution.

3 . The method of claim 2 , wherein the second noise distribution is based on a statistical analysis of other computing devices reporting corresponding events associated with the function of the computing device over a previous period of time.

4 . The method of claim 1 , further comprising:

detecting an initial plurality of events associated with the function of the computing device over a previous period of time, the previous period of time occurring prior to the period of time;

adding a random noise to information associated with the initial plurality of events; and

sending the information including the random noise to the device usage service.

5 . The method of claim 1 , further comprising:

detecting a subsequent plurality of events in a subsequent period of time associated with the function of the computing device, the subsequent period of time occurring after the period of time; and

adding a third noise to a value associated with the subsequent plurality of events, wherein the third noise is associated with a first noise distribution.

6 . The method of claim 1 , wherein the first noise and the second noise are configured to disambiguate regular usage of the function and irregular usage of the function.

7 . The method of claim 1 , wherein determining the first noise associated with the plurality of events over the period of time comprises:

determining a first random value; and

adding the first random value to a previous random value to generate the first noise.

8 . The method of claim 1 , wherein the second noise is associated with the function of the computing device and is added to reports identifying the usage of the function.

9 . A method of distributing noise models to anonymize reporting data, the method comprising:

receiving a first plurality of reports from a plurality of computing devices, wherein the first plurality of reports include values identifying usage of a function at a corresponding computing device combined with a first random noise value generated at the corresponding computing device;

generating a first noise distribution based on the first plurality of reports;

sending the first noise distribution to the plurality of computing devices; and

receiving a second plurality of reports from the plurality of computing devices, wherein the second plurality of reports include values identifying usage of the function at the corresponding computing device combined with a second random noise value generated at the corresponding computing device based on the first noise distribution.

10 . The method of claim 9 , further comprising:

generating a second noise distribution based on the second plurality of reports; and

sending the second noise distribution to the plurality of computing devices.

11 . The method of claim 9 , wherein the second random noise value includes a first noise associated with the first noise distribution and a second noise generated based on a different noise distribution.

12 . An apparatus for receiving privacy-protected usage information, comprising:

at least one memory; and

at least one processor coupled to the at least one memory and configured to:

detect, over a period of time, a plurality of events associated with a function of the apparatus;

determine a first noise associated with the plurality of events over the period of time;

add the first noise and a second noise to a value corresponding to the plurality of events, wherein the second noise is independent of the first noise; and

send a noisy report identifying a usage of the function to a device usage service, the noisy report including the value with the first noise and the second noise.

13 . The apparatus of claim 12 , wherein the at least one processor is configured to:

receive a second noise distribution from the device usage service, wherein the second noise is generated based on the second noise distribution.

14 . The apparatus of claim 13 , the second noise distribution is based on a statistical analysis of other computing devices reporting corresponding events associated with the function of the apparatus over a previous period of time.

15 . The apparatus of claim 12 , wherein the at least one processor is configured to:

detect an initial plurality of events associated with the function of the apparatus over a previous period of time, the previous period of time occurring prior to the period of time;

add a random noise to information associated with the initial plurality of events; and

send the information including the random noise to the device usage service.

16 . The apparatus of claim 12 , wherein the at least one processor is configured to:

detect a subsequent plurality of events in a subsequent period of time associated with the function of the apparatus, the subsequent period of time occurring after the period of time; and

add a third noise to a value associated with the subsequent plurality of events, wherein the third noise is associated with a first noise distribution.

17 . The apparatus of claim 12 , the first noise and the second noise are configured to disambiguate regular usage of the function and irregular usage of the function.

18 . The apparatus of claim 12 , wherein the at least one processor is configured to:

determine a first random value; and

add the first random value to a previous random value to generate the first noise.

19 . The apparatus of claim 12 , the second noise is associated with the function of the apparatus and is added to reports identifying the usage of the function.

20 . An apparatus for receiving privacy-protected usage information, comprising:

at least one memory; and

at least one processor coupled to at least one memory and configured to:

receive a first plurality of reports from a plurality of computing devices, wherein the first plurality of reports include values identifying usage of a function at a corresponding computing device combined with a first random noise value generated at the corresponding computing device;

generate a first noise distribution based on the first plurality of reports;

send the first noise distribution to the plurality of computing devices; and

receive a second plurality of reports from the plurality of computing devices, wherein the second plurality of reports include values identifying usage of the function at the corresponding computing device combined with a second random noise value generated at the corresponding computing device based on the first noise distribution.

21 . The apparatus of claim 20 , wherein the at least one processor is configured to:

generate a second noise distribution based on the second plurality of reports; and

send the second noise distribution to the plurality of computing devices.

22 . The apparatus of claim 20 , the second random noise value includes a first noise associated with the first noise distribution and a second noise generated based on a different noise distribution.