Auto-generated synthetic identities for simulating population dynamics to detect fraudulent activity

• US 10,484,426 B2
• Filed: 03/11/2019
• Issued: 11/19/2019
• Est. Priority Date: 03/12/2018
• Status: Active Grant

• Current Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Original Assignee: Capital One Services LLC (Capital One Financial Corporation)
• Inventors: Sherif, Timur, Jouhikainen, Hannes, Blanchet, Steve
• Primary Examiner(s): Simitoski, Michael
• Application Number:
  US16/298,170
• Publication Number:
  US 20190281086A1
• Time in Patent Office: 253 Days
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety
• CPC Class Codes: H04L 63/102 Entity profiles
• CPC Class Codes: H04L 63/1466 Active attacks involving interception, injection, modification, spoofing of data unit addresses, e.g. hijacking, packet injection or TCP sequence number attacks
• CPC Class Codes: H04L 63/1491 using deception as countermeasure, e.g. honeypots, honeynets, decoys or entrapment
• CPC Class Codes: H04W 12/12 Detection or prevention of fraud

Abstract

Embodiments disclosed herein generally relate to a system and method for detecting fraudulent computer activity. A computing system generates a plurality of synthetic identities. Each of the plurality of synthetic identities mimics information associated with a verified identity. The computing system receives, from a user, an input attempt. The input attempt includes a synthetic identity of the plurality of synthetic identities. The computing system compares input information in the input attempt to the plurality of synthetic identities. The computing system determines that the input information in the input attempt includes information from the plurality of synthetic identities, if it does, the computing system rejects the input attempt.

Claims

1. A method, comprising:

generating, by a computing system using a machine learning model, a synthetic identity model by learning a plurality of characteristics associated with a verified identity using a training data set comprising sets of verified information;

generating, by the computing system, a plurality of synthetic identities using the synthetic identity model, wherein each synthetic identity mimics information associated with a verified identity;

receiving, by the computing system from a client device, an input attempt comprising input information associated with a synthetic identity of the plurality of synthetic identities;

comparing the input information in the input attempt to the plurality of synthetic identities;

determining that the input information in the input attempt comprises information from the plurality of synthetic identities; and

rejecting the input attempt.

2. The method of claim 1, wherein generating, by the computing system using the machine learning model, the synthetic identity model by learning the plurality of characteristics associated with the verified identity using the training data set, comprises:

learning how to create synthetic identities that mimic information associated with verified identities.

3. The method of claim 1, wherein generating, by the computing system, the plurality of synthetic identities using the synthetic identity model, comprises:

referencing each generated synthetic identity against one or more third party data sources to verify that a candidate synthetic identity does not correspond to a verified identity.

4. The method of claim 1, further comprising:

identifying, by the computing system, an Internet protocol (IP) address of the user attempting to use information from the plurality of synthetic identities;

identifying, by the computing system, a further input attempt originating from the IP address; and

blocking, by the computing system, the further input attempt.

5. The method of claim 1, further comprising:

uploading, by the computing system, the plurality of synthetic identities into a darkweb accessible web page.

6. The method of claim 1, wherein generating, by the computing system using the machine learning model, the synthetic identity model by learning the plurality of characteristics associated with a verified identity comprises:

scanning a plurality of sources of verified identity information to identify characteristics of verified identities.

7. The method of claim 1, wherein generating, by the computing system, the plurality of synthetic identities using the synthetic identity model comprises:

injecting indicia or combinations of indicia into each synthetic identity such that each synthetic identity is detectable by the computing system.

8. The method of claim 1, further comprising:

receiving, by the computing system from the client device, a footprint associated with the input attempt; and

referencing, by the computing system, the footprint in analysis of further input attempts.

9. A system, comprising:

a processor; and

a memory having programming instructions stored thereon, which, when executed by the processor, perform operations comprising;

generating, using a machine learning model, a synthetic identity model by learning a plurality of characteristics associated with a verified identity using a training data set comprising sets of verified information;

generating a plurality of synthetic identities using the synthetic identity model, wherein each synthetic identity mimics information associated with a verified identity;

receiving, from a client device, an input attempt comprising input information associated with a synthetic identity of the plurality of synthetic identities;

comparing the input information in the input attempt to the plurality of synthetic identities;

determining that the input information in the input attempt comprises information from the plurality of synthetic identities; and

rejecting the input attempt.

10. The system of claim 9, wherein generating, using the machine learning model, the synthetic identity model by learning the plurality of characteristics associated with the verified identity using the training data set, comprises:

learning how to create synthetic identities that mimic information associated with verified identities.

11. The system of claim 9, wherein generating the plurality of synthetic identities using the synthetic identity model, comprises:

referencing each generated synthetic identity against one or more third party data sources to verify that a candidate synthetic identity does not correspond to a verified identity.

12. The system of claim 9, wherein the operations further comprise:

identifying an Internet protocol (IP) address of the user attempting to use information from the plurality of synthetic identities;

identifying a further input attempt originating from the IP address; and

blocking the further input attempt.

13. The system of claim 9, wherein the operations further comprise:

uploading the plurality of synthetic identities into a darkweb accessible web page.

14. The system of claim 9, wherein generating, using the machine learning model, the synthetic identity model by learning the plurality of characteristics associated with a verified identity comprises:

scanning a plurality of sources of verified identity information to identify characteristics of verified identities.

15. The system of claim 9, wherein generating the plurality of synthetic identities using the synthetic identity model comprises:

injecting indicia or combinations of indicia into each synthetic identity such that each synthetic identity is detectable by the system.

16. The system of claim 9, wherein the operations comprises:

receiving, by a client device, a footprint associated with the input attempt; and

referencing the footprint in analysis of further input attempts.