Secured analytics using encrypted data

Patent metadata

Field	Value
Publication number	US-11907952-B2
Application number	US-202016815972-A
Country	US
Kind code	B2
Filing date	Mar 11, 2020
Priority date	Mar 12, 2019
Publication date	Feb 20, 2024
Grant date	Feb 20, 2024

Abstract

Devices, systems, and methods are provided for performing secured analytics using encrypted data. The method may include receiving first data and second data, the first data and the second data being homomorphically encrypted, the first data associated with a first type of data, and the second data associated with a second type of data. The method may include retrieving third data associated with the first type of data, and retrieving fourth data associated with the second type of data. The method may include determining a first proximity between the first data and the third data, and determining a second proximity between the second data and the fourth data. The method may include determining, based on the first proximity and the second proximity, a risk score, and determining, based on the risk score, a fraudulent action associated with the first data and the second data.

First claim

That which is claimed:

1. A method, comprising:
receiving, by at least one processor of a device, first data and second data, the first data and the second data being homomorphically encrypted, the first data comprising a name of a user, and the second data comprising at least one of a social security number or a payment account of the user;
retrieving, by the at least one processor, third data comprising name data, the third data being homomorphically encrypted;
retrieving, by the at least one processor, fourth data comprising at least one of social security number data or payment account data, the fourth data being homomorphically encrypted;
determining, by the at least one processor, a first proximity between the first data and the third data;
determining, by the at least one processor, a second proximity between the second data and the fourth data, wherein the first proximity and the second proximity are unassociated with an authentication using biometric data;
determining, by the at least one processor, based on a comparison of the first proximity to a first proximity threshold and based on a comparison of the second proximity to a second proximity threshold different than the first proximity threshold; a risk score associated with opening a user account based on the first data and the second data; and
identifying, by the at least one processor and based on the risk score, a fraudulent action associated with opening the user account based on the first data and the second data.

2. The method of claim 1 , wherein the first data and the third data remain homomorphically encrypted while determining the first proximity, and wherein the second data and the fourth data remain homomorphically encrypted while determining the second proximity.

3. The method of claim 2 , wherein the first data comprises first ciphertext, and wherein the second data comprises second ciphertext.

4. The method of claim 1 , further comprising:
determining that the first proximity is less than the first proximity threshold; and
determining, based on the first proximity being less than the first proximity threshold, fifth data and sixth data, the fifth data and the sixth data associated with an account attribute,
wherein determining the risk score is further based on a comparison of the fifth data to the sixth data.

5. The method of claim 4 , wherein the first data, the second data, and the fifth data are associated with a request to open the user account.

6. The method of claim 5 , wherein the fraudulent action indicates that the user account is fraudulent.

7. The method of claim 4 , wherein the account attribute is an address associated with the user account.

8. The method of claim 1 , wherein the first data comprises first ciphertext, wherein the third data comprises second ciphertext, and wherein the first proximity is a Levenshtein-Damereau distance between the first ciphertext and the second ciphertext.

9. The method of claim 8 , further comprising determining that the Levenshtein-Damereau distance is less than the first proximity threshold.

10. A system comprising memory coupled to at least one processor, the at least one processor configured to:
receive first data and second data, the first data and the second data being homomorphically encrypted, the first data comprising a name of a user, and the second data comprising at least one of a social security number or a payment account of the user;
retrieve third data comprising name data, the third data being homomorphically encrypted;
retrieve fourth data comprising at least one of social security number data or payment account data, the fourth data being homomorphically encrypted;
determine a first proximity between the first data and the third data;
determine a second proximity between the second data and the fourth data, wherein the first proximity and the second proximity are unassociated with an authentication using biometric data;
determine based on a comparison of the first proximity to a first proximity threshold and based on a comparison of the second proximity to a second proximity threshold different than the first proximity threshold a risk score associated with opening a user account based on the first data and the second data; and
identify, based on the risk score, a fraudulent action associated with opening the user account based on the first data and the second data.

11. The system of claim 10 , wherein the first data and the third data remain homomorphically encrypted while determining the first proximity, and wherein the second data and the fourth data remain homomorphically encrypted while determining the second proximity.

12. The system of claim 11 , wherein the first data comprises first ciphertext, and wherein the second data comprises second ciphertext.

13. The system of claim 10 , wherein the at least one processor is further configured to:
determine that the first proximity is less than the first proximity threshold; and
determine, based on the first proximity being less than the first proximity threshold, fifth data and sixth data, the fifth data and the sixth data associated with an account attribute,
wherein to determine the risk score is further based on a comparison of the fifth data to the sixth data.

14. The system of claim 13 , wherein the first data, the second data, and the fifth data are associated with a request to open the user account.

15. The system of claim 14 , wherein the fraudulent action indicates that the user account is fraudulent.

16. The system of claim 13 , wherein the account attribute is an address associated with the user account.

17. The system of claim 10 , wherein the first data is an address associated with the user account.

18. A non-transitory computer-readable medium storing computer-executable instructions which, when executed by a processor, cause the processor to perform operations comprising:
receiving first data and second data, the first data and the second data being homomorphically encrypted, the first data comprising a name of a user, and the second data comprising at least one of a social security number or payment account of the user;
retrieving third data comprising name data, the third data being homomorphic ally encrypted;
retrieving fourth data comprising at least one of social security number data or payment account data, the fourth data being homomorphically encrypted;
determining a first proximity between the first data and the third data, the first proximity greater than zero;
determining a second proximity between the second data and the fourth data, wherein the first proximity and the second proximity are unassociated with an authentication using biometric data;
determining based on a comparison of the first proximity to a first proximity threshold and based on a comparison of the second proximity to a second proximity threshold different than the first proximity threshold, a risk score associated with opening a user account based on the first data and the second data; and
identifying, based on the risk score, a fraudulent action associated with opening the user account based on the first data and the second data.

19. The non-transitory computer-readable medium of claim 18 , wherein the first data and the third data remain homomorphically encrypted while determining the first proximity, and wherein the second data and the fourth data remain homomorphically encrypted while determining the second proximity.

20. The non-transitory computer-readable medium of claim 18 , wherein the fi

Assignees

• Cox Communications Inc

Inventors

• Patel Jignesh
• Tang Harry
• Carothers Matthew Edwin

Classifications

• G06Q20/4016 Primary

  involving fraud or risk level assessment in transaction processing · CPC title

• G06F21/602

  Providing cryptographic facilities or services · CPC title

• G06Q20/382

  insuring higher security of transaction · CPC title

• H04L9/008 Primary

  involving homomorphic encryption · CPC title

• H04L9/0618

  Block ciphers, i.e. encrypting groups of characters of a plain text message using fixed encryption transformation · CPC title