Systems and methods for generating user profiles

1. A computer-implemented method for generating user profiles, at least a portion of the method being performed by a computing device comprising at least one processor, the method comprising:

analyzing a data set of user profiles for services and creating, by applying a machine learning protocol to the data set of user profiles, a generative model that generates new user profiles for users rather than the users manually creating the user profiles;

detecting, by a detection module, a measurement of obfuscation that users previously applied to a specific attribute when manually creating user profiles for a specific service;

applying, by an application module, the measurement of obfuscation that users previously applied to the specific attribute of the user profiles to true data for a new user by fuzzing the true data to create a fuzzed value; and

generating automatically a new user profile for a user of the specific service by populating the specific attribute within the new user profile with the fuzzed value;

comparing, by the detection module, by the detection module, a more accurate set of information describing users with historical user profiles that the users manually generated, wherein the detection module learns both a set of items of information the users preferred to reveal and a set of items of information the users preferred to omit; and

protecting, by the application module, the privacy of the user by denying a request for data describing the user or reducing a level of accuracy of the true data when creating the fuzzed value to a degree that matches how the users manually performed a previous task of fuzzing.

2. The computer-implemented method of claim 1 , further comprising performing a security action to protect the privacy of the new user corresponding to the new user profile.

3. The computer-implemented method of claim 2 , wherein the security action comprises

alerting the new user to the request for data describing the user.

4. The computer-implemented method of claim 1 ,

wherein the generative model either:

matches the measurement of obfuscation to the specific service; or

matches the measurement of obfuscation to a combination of the specific service and the specific attribute.

5. The computer-implemented method of claim 1 , wherein the specific attribute comprises at least one of:

a location of the new user; or

a birthday of the new user.

6. The computer-implemented method of claim 1 , wherein analyzing the data set of user profiles comprises detecting that users previously fuzzed values for the specific attribute by at least one of:

omitting a field of true data for the specific attribute; or

generating random data for the specific attribute.

7. The computer-implemented method of claim 1 , wherein the data set of user profiles is derived from a password management system.

8. The computer-implemented method of claim 1 , wherein the specific attribute comprises a picture of the new user.

9. The computer-implemented method of claim 1 , wherein the specific attribute comprises a name of the new user.

10. The computer-implemented method of claim 1 , wherein the data set of user profiles is derived from an identity management system.

11. A system for generating user profiles, the system comprising:

an analysis module, stored in memory, that analyzes a data set of user profiles for services and creates, by applying a machine learning protocol to the data set of user profiles, a generative model that generates new user profiles for users rather than the users manually creating the user profiles;

a detection module, stored in memory, that detects a measurement of obfuscation that users previously applied to a specific attribute when manually creating user profiles for a specific service;

an application module, stored in memory, that applies the measurement of obfuscation that users previously applied to the specific attribute of the user profiles to true data for a new user by fuzzing the true data to create a fuzzed value;

a generation module, stored in memory, that generates automatically a new user profile for a user of the specific service by populating the specific attribute within the new user profile with the fuzzed value; and

at least one physical processor configured to execute the analysis module, the detection module, the application module, and the generation module;

wherein:

the detection module further compares a more accurate set of information describing users with historical user profiles that the users manually generated, wherein the detection module learns both a set of items of information the users preferred to reveal and a set of items of information the users preferred to omit; and

the application module protects the privacy of the user by denying a request for data describing the user or reducing a level of accuracy of the true data when creating the fuzzed value to a degree that matches how the users manually performed a previous task of fuzzing.

12. The system of claim 11 , wherein the generation module is further configured to perform a security action to protect the privacy of the new user corresponding to the new user profile.

13. The system of claim 12 , wherein the security action comprises

denying a request for the user data; or

alerting the new user to the request for data describing the user.

14. The system of claim 11 , wherein the generative model either:

matches the measurement of obfuscation to the specific service; or

matches the measurement of obfuscation to a combination of the specific service and the specific attribute.

15. The system of claim 11 , wherein the specific attribute comprises at least one of:

a location of the new user; or

a birthday of the new user.

16. The system of claim 11 , wherein the analysis module analyzes the data set of user profiles by detecting that users previously fuzzed values for the specific attribute by at least one of:

omitting a field of true data for the specific attribute; or

generating random data for the specific attribute.

17. The system of claim 11 , wherein the data set of user profiles is derived from a password management system.

18. The system of claim 11 , wherein the specific attribute comprises a picture of the new user.

19. The system of claim 11 , wherein the specific attribute comprises a name of the new user.

20. A non-transitory computer-readable medium comprising one or more computer-readable instructions that, when executed by at least one processor of a computing device, cause the computing device to:

analyze a data set of user profiles for services and creating, by applying a machine learning protocol to the data set of user profiles, a generative model that generates new user profiles for users rather than the users manually creating the user profiles;

detect, by a detection module, a measurement of obfuscation that users previously applied to a specific attribute when manually creating user profiles for a specific service;

apply, by an application module, the measurement of obfuscation that users previously applied to the specific attribute of the user profiles to true data for a new user by fuzzing the true data to create a fuzzed value; and

generate automatically a new user profile for a user of the specific service by populating the specific attribute within the new user profile with the fuzzed value;

compare, by the detection module, a more accurate set of information describing users with historical user profiles that the users manually generated, wherein the detection module learns both a set of items of information the users preferred to reveal and a set of items of information the users preferred to omit; and

protect, by the application module, the privacy of the user by denying a request for data describing the user or reducing a level of accuracy of the true data when creating the fuzzed value to a degree that matches how the users manually performed a previous task of fuzzing.