Scrambling an identity on the internet

Patent metadata

Field	Value
Publication number	US-12417315-B2
Application number	US-202318197443-A
Country	US
Kind code	B2
Filing date	May 15, 2023
Priority date	May 15, 2023
Publication date	Sep 16, 2025
Grant date	Sep 16, 2025

Abstract

Aspects described herein may obfuscate publicly available personal information by publishing generated synthetic user personal data to one or more sites. By publishing the generated synthetic personal data to one or more sites, a user's actual personal data will be more difficult to discern and/or detect, resulting in greater privacy, security, and/or control of personal information. A machine learning model may be trained to generate synthetic personal data based on verified personal data and/or training datasets. Upon receiving a request from a user, the machine learning model may generate synthetic personal data, which appears similar to the publicly available information but includes false and/or inaccurate data and/or information about the user. The generated synthetic personal data and/or information may be disseminated to a plurality of sites to hide, or otherwise obfuscate, the user's actual data and/or information.

First claim

The invention claimed is:

1. A method comprising:
receiving, by a server from a user device associated with a user, a request to obfuscate publicly available personal data associated with the user;
retrieving, by the server from a database associated with the server, verified personal data associated with the user, wherein the verified personal data comprises personal information vetted by one or more government entities;
training, by the server using a training dataset, a machine learning model to generate synthetic personal data, wherein the training dataset comprises at least one of: a commercial training dataset, a previously constructed training dataset, or verified personal data associated with the user;
generating, by the server using the trained machine learning model and based on the verified personal data, synthetic personal data associated with the user; and
disseminating, by the server and based on receiving approval to disseminate the synthetic personal data from the user device, the synthetic personal data on the Internet.

2. The method of claim 1 , further comprising:
before disseminating the synthetic personal data, calculating, by the server, a difference value between the synthetic personal data and the verified personal data, wherein disseminating the synthetic personal data on the Internet is based on a determination that the difference value satisfies a threshold.

3. The method of claim 2 , further comprising:
calculating, by the server, a similarity value between the synthetic personal data and the verified personal data, wherein disseminating the synthetic personal data on the Internet is further based on a determination that the similarity value satisfies a second threshold.

4. The method of claim 1 , wherein disseminating the synthetic personal data comprises:
creating, by the server, a dummy social media account associated with the user;
publishing, by the server, the dummy social media account to the Internet; and
uploading, by the server, the synthetic personal data to the published dummy social media account.

5. The method of claim 1 , further comprises:
disseminating, by the server, synthetic personal data to a Tor network.

6. The method of claim 1 , wherein the synthetic personal data comprises at least one of:
a name;
a phone number;
an address;
an e-mail;
an image;
a video;
an audio file;
a username;
a social media handle;
a bank account number;
a credit card number;
a social security number; or
a date of birth.

7. The method of claim 1 , wherein the disseminating the synthetic personal data on the Internet comprises at least one of:
posting the synthetic personal data to a social media website;
publishing an article containing the synthetic personal data to a news website; or
publishing a blog post that comprises the synthetic personal data.

8. The method of claim 1 , wherein the machine learning model comprises at least one of:
a supervised machine learning model;
an unsupervised machine learning model; or
a semi-supervised machine learning model.

9. The method of claim 1 , wherein the machine learning model comprises at least one of:
a generative adversarial network (GAN); or
a conditional generative adversarial network (cGAN).

10. A computing device, comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the computing device to:
receive, from a user device associated with a user, a request to obfuscate publicly available personal data associated with the user;
monitor one or more public sites for publicly available personal data associated with the user;
generate, using a trained machine learning model and based on a comparison of the publicly available personal data to verified personal data associated with the user, synthetic personal data associated with the user, wherein the synthetic personal data comprises data configured to appear similar to verified personal data associated with the user while being different from verified personal data associated with the user; and
disseminate, based on locating publicly available personal data associated with the user and based on receiving approval to disseminate the synthetic personal data from the user device, the synthetic personal data to one or more public sites.

11. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
calculate, before disseminating the synthetic personal data to a public site, a difference value between the synthetic personal data and the verified personal data, wherein disseminating the synthetic personal data to a public site is based on a determination that the difference value between the synthetic personal data and the verified personal data satisfies a threshold.

12. The computing device of claim 10 , wherein the one or more public sites comprise at least one of:
a social media website;
a news website;
a blog post;
a Tor network;
an intranet;
a social media account; or
a software app.

13. The computing device of claim 10 , wherein the synthetic personal data comprises at least one of:
a name;
a phone number;
an address;
an e-mail;
an image;
a video;
an audio file;
a username;
a social media handle;
a bank account number;
a credit card number;
a social security number; or
a date of birth.

14. The computing device of claim 10 , wherein the instructions, when executed by the one or more processors, cause the computing device to:
locate publicly available personal data associated with the user on a user's social media account;
remove one or more entries from one or more of the user's social media accounts; and
publish synthetic personal data to the one or more of the user's social media accounts.

15. The computing device of claim 10 , wherein the machine learning model comprises at least one of:
a supervised machine learning model;
an unsupervised machine learning model; or
a semi-supervised machine learning model.

16. The computing device of claim 10 , wherein the machine learning model comprises at least one of:
a generative adversarial network (GAN); or
a conditional generative adversarial network (cGAN).

17. A non-transitory computer readable medium storing instruction that, when executed by one or more processors, cause a computing device to perform steps comprising:
receiving, from a user device associated with a user, a request to obfuscate publicly available personal data associated with the user;
monitoring one or more public sites for publicly available personal data associated with the user;
generating, using a trained machine learning model and based on a comparison of the publicly available personal data to verified personal data associated with the user, synthetic personal data associated with the user of the user device, wherein the synthetic personal data is configured to appear similar to verified personal data associated with the user, while being different; and
disseminating, based on locating publicly available personal data associated with the user in a public sites and based on receiving approval to disseminate the synthetic personal data from the user device, the synthetic personal data to the public sites.

18. The non-transitory computer readable medium of claim 17 , wherein the instruction, when executed by the one or more processors, cause the computing device to perform steps comprising:
calculating, before disseminating the synthetic personal d

Assignees

• Capital One Services Llc

Inventors

• Rapowitz Samuel
• Yee Bryant
• Stone Armando Martinez

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F21/6254 Primary

  by anonymising data, e.g. decorrelating personal data from the owner's identification · CPC title

• G06F21/6245

  Protecting personal data, e.g. for financial or medical purposes · CPC title

• H04L63/0421

  Anonymous communication, i.e. the party's identifiers are hidden from the other party or parties, e.g. using an anonymizer · CPC title

• H04L67/02 Primary

  based on web technology, e.g. hypertext transfer protocol [HTTP] · CPC title