Privacy personas using synthetic personally identifiable information

1. A method comprising:

receiving, by one or more processors into a non-transitory machine-readable medium, a form having one or more fields for receiving personally identifying information (PII);

receiving, by the one or more processors, input data for the form, the input data comprising source PII;

modelling, by the one or more processors, the characteristics of the source PII to generate a model associated with the form;

generating, by the one or more processors, synthetic PII based, at least in part, the source PII and the model;

providing, by the one or more processors, the synthetic PII to the one or more fields of the form;

receiving, by the one or more processors, a distortion indicator via a user interface element associated with the one or more fields of the form, wherein the user interface element is a knob or a slider actuated by a user to indicate how much to distort data associated with one or more fields of the form wherein generating the synthetic PII comprises generating the synthetic PII based, at least in part, on the distortion indicator; and

determining, by the one or more processors, whether the received PII for the one or more fields is fake, and determining, by the one or more processors, whether the synthetic PII for the one or more fields is plausible.

2. The method of claim 1 , further comprising:

receiving, by the one or more processors, an indication that source PII is to be preserved for a subset of the one or more fields; and

providing, by the one or more processors, the source PII to the subset of the one or more fields.

3. The method of claim 1 , further comprising:

receiving, by the one or more processors, demographic characteristics;

wherein generating the synthetic PII comprises generating the synthetic PII based, at least in part, on the demographic characteristics.

4. The method of claim 1 , further comprising:

receiving, by the one or more processors, a region indicator;

wherein generating the synthetic PII comprises generating the synthetic PII based, at least in part, on the region indicator.

5. The method of claim 1 , further comprising:

generating, by the one or more processors, one or more machine learning models based on training data, the training data comprising PII;

wherein generating the model associated with the form comprises generating the model, based at least in part, on the one or more machine learning models.

6. The method of claim 5 , further comprising:

submitting the form to a service application;

receiving feedback for at least one field of the form from the service application;

storing the feedback as updated training data;

updating the machine learning models based, at least in part on the updated training data.

7. The method of claim 1 , further comprising:

adding a fingerprint to field data for the one or more fields for receiving PII;

storing the fingerprint;

submitting the form including the field data to a service application;

receiving leaked data from third party system; and

generating an indication that the service application has experienced a data breach in response to determining that the fingerprint is present in the leaked data.

8. The method of claim 1 , wherein the source PII comprises true PII for a user.

9. The method of claim 1 , wherein the source PII comprises PII of a randomly selected persona.

10. The method of claim 1 , wherein determining, by the one or more processors, whether the received PII for the one or more fields is fake, comprises analyzing the information provided by a user for the one or more fields and determining whether the information is untrue or unreal.

11. The method of claim 1 , wherein determining, by the one or more processors, whether the synthetic PII for the one or more fields is plausible, comprises determining if the synthetic PII for any one of the one or more fields: has a proper syntax, is of the correct data type, and is not inconsistent with synthetic PII for any other one of the one or more fields.

12. The method of claim 1 , wherein upon determining, by the one or more processors, that the received PII for the one or more fields is fake or that the synthetic PII for the one or more fields is not plausible, notifying the user, by the one or more processors, and refusing, by the one or more processors, access to content or services.

13. A system comprising:

one or more processors; and

a machine-readable medium accessible to the one or more processors and storing instructions that, when executed, cause the one or more processors to:

receive a form having one or more fields for receiving personally identifying information (PII),

receive input data for the form, the input data comprising source PII,

receive a distortion indicator via a user interface element associated with the one or more fields of the form, wherein the user interface element is a knob or a slider actuated by a user to indicate how much to distort data associated with one or more fields of the form,

model the characteristics of the source PII to generate a model associated with the form,

generate synthetic PII based, at least in part, the source PII, the distortion indicator, and the model,

provide the synthetic PII to the one or more fields of the form, and

determine whether the received PII for the one or more fields is fake, and determine whether the synthetic PII for the one or more fields is plausible.

14. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

receive a distortion indicator;

wherein the instructions to generate the synthetic PII comprise instructions to generate the synthetic PII based, at least in part, on the distortion indicator.

15. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

determine whether the synthetic PII for the one or more fields is semantically correct when combined.

16. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

receive an indication that source PII is to be preserved for a subset of the one or more fields; and

provide the source PII to the subset of the one or more fields.

17. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

receive demographic characteristics;

wherein the instructions to generate the synthetic PII comprise instructions to generate the synthetic PII based, at least in part, on the demographic characteristics.

18. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

receiving a region indicator;

wherein the instructions to generate the synthetic PII comprise instructions to generate the synthetic PII based, at least in part, on the region indicator.

19. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

generate one or more machine learning models based on training data, the training data comprising PII;

wherein the instructions to generate the model associated with the form comprise instructions to generate the model, based at least in part, on the one or more machine learning models.

20. The system of claim 19 , wherein the instructions further comprise instructions to cause the one or more processors to:

submit the form to a service application;

receive feedback for at least one field of the form from the service application;

store the feedback as updated training data;

update the machine learning models based, at least in part on the updated training data.

21. The system of claim 13 , wherein the instructions further comprise instructions to cause the one or more processors to:

add a fingerprint to field data for the one or more fields for receiving PII;

store the fingerprint;

submit the form including the field data to a service application;

receive leaked data from third party system; and

generate an indication that the service application has experienced a data breach in response to determining that the stored fingerprint is present in the leaked data.

22. The system of claim 13 , wherein the source PII comprises true PII of a user.

23. The system of claim 13 , wherein the source PII comprises PII of a randomly selected persona.

24. A machine-readable medium having processor executable instructions, that when executed, cause one or more processors to:

receive a form having one or more fields for receiving personally identifying information (PII),

receive input data for the form, the input data comprising source PII,

model the characteristics of the source PII to generate a model associated with the form,

generate synthetic PII based, at least in part, the source PII and the model,

provide the synthetic PII to the one or more fields of the form;

receive a distortion indicator via a user interface element associated with the one or more fields of the form, wherein the user interface element is a knob or a slider actuated by a user to indicate how much to distort data associated with one or more fields of the form, wherein generating the synthetic PII comprises generating the synthetic PII based, at least in part, on the distortion indicator; and

determine whether the received PII for the one or more fields is fake, and determine whether the synthetic PII for the one or more fields is plausible.