IP Library › Granted Patent US 12,210,601
Granted Patent B2
US 12,210,601 · App. 17/272,258 · Granted Jan 28, 2025

Decentralized biometric identification and authentication network

Inventors: Eyal S. Goldwerger (New York, NY); Elad Bullkich (New York, NY); Eran Mitrani (New York, NY)
Assignee: Anonybit, Inc.
G06F21/32G06N20/00H04L9/3218
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,210,601
App. No.
17/272,258
Granted
Jan 28, 2025
Kind
B2
Abstract

A measurement unit of multiple measurement units is received. The measurement unit represents a portion of a biometric measurement of a user in response to a request to authenticate the user. Whether the measurement unit corresponds to a template unit of multiple template units is determined. The template unit represents a portion of a biometric template that represents a characteristic of the user that distinguishes the user from other users. Responsive to determining that the measurement unit corresponds to the template unit, a sub-result of multiple sub-results is determined based on a comparison between the measurement unit and the template unit. The sub-result indicates a similarity between the measurement unit and the template unit. The sub-result is sent to a node of the multiple nodes. The authentication of the user is based at least in part on the sub-result.

Claims (75)

1. A system for authentication of a user comprising:

a decentralized network of electronic devices comprising a first subset of a plurality of nodes, wherein each of the first subset of nodes is configured to:

receive a measurement unit of a plurality of measurement units in response to a request to authenticate the user, wherein each of the plurality of measurement units received represents a less-than-complete portion of a complete biometric measurement provided by the user in conjunction with the request to authenticate the user;

determine a sub-result of a plurality of sub-results based on a comparison between the measurement unit and a template unit of a plurality of template units, wherein each of the plurality of template units corresponds to a respective less-than-complete portion of a complete biometric template previously provided by the user, wherein the complete biometric template previously provided by the user represents a characteristic of the user that distinguishes the user from other users, and wherein the sub-result indicates a level of similarity between the measurement unit and the template unit; and

send the sub-result to a node of a second subset of the plurality of nodes, wherein authentication of the user is based at least in part on the sub-result.

2. The system of claim 1 , wherein each of the first subset of nodes is further configured to:

determine whether the measurement unit corresponds to the template unit based on a comparison between an identifier of the measurement unit and an identifier of the template unit, wherein the determination of the sub-result is responsive to determining that the measurement unit corresponds to the template unit.

3. The system of claim 1 , wherein to determine the sub-result based on the comparison between the measurement unit and the template unit, each of the first subset of nodes is configured to: determine a distance between the measurement unit and the template unit, wherein the sub-result comprises an indication of the determined distance.

4. The system of claim 3 ,

wherein the measurement unit comprises a first vector coordinate of a first vector in Euclidian space and the template unit comprises a second vector coordinate of a second vector in the Euclidian space, and

wherein the determined distance is a distance between the first vector coordinate the second vector coordinate in the Euclidian space.

5. The system of claim 4 ,

wherein the biometric measurement has been transformed using a machine learning model into the first vector comprising a first plurality of vector coordinates in the Euclidian space,

wherein the biometric template has been transformed using the machine learning model into the second vector comprising a second plurality of vector coordinates.

6. The system of claim 1 , further comprising the second subset of the plurality of nodes, wherein each of the second subset of nodes is configured to:

aggregate one or more sub-results received from one or more nodes of the first subset of nodes into a sub-result grouping; and

send the sub-result groupings to an arbiter node of the plurality of nodes, wherein the second subset of nodes each send a respective sub-result grouping of a plurality of sub-result groupings to the arbiter node.

7. The system of claim 6 , further comprising the arbiter node, wherein the arbiter node is configured to:

determine an authentication result based on the plurality of sub-result groupings, wherein the authentication result indicates whether the user is authenticated; and

send the authentication result to a device associated with the request to authenticate the user.

8. The system of claim 1 , wherein the authentication of the user is based on a zero-knowledge authentication technique where none of the plurality of nodes has a complete knowledge of the biometric template.

9. A system for authentication of a user comprising:

a memory; and

a processing device of a first node of a plurality of nodes, the processing device coupled to the memory, wherein the processing device is configured to:

receive a measurement unit of a plurality of measurement units in response to a request to authenticate the user, wherein each of the plurality of measurement units received represents a less-than-complete portion of a complete biometric measurement provided by the user;

determine whether the measurement unit corresponds to a template unit of a plurality of template units, wherein each of the plurality of template units represents a respective less-than-complete portion of a complete biometric template previously provided by the user, wherein the complete biometric template previously provided by the user represents a characteristic of the user that distinguishes the user from other users;

responsive to determining that the measurement unit corresponds to the template unit, determine a sub-result of a plurality of sub-results based on a comparison between the measurement unit and the template unit, wherein the sub-result indicates a level of similarity between the measurement unit and the template unit; and

send the sub-result to a second node of the plurality of nodes, wherein the authentication of the user is based at least in part on the sub-result.

10. The system of claim 9 , wherein the processing device is further configured to:

receive, from a third node of the plurality of nodes, the template unit of the plurality of template units.

11. The system of claim 10 , wherein the template unit is an encrypted template unit, wherein the processing device is further configured to:

decrypt the encrypted template unit using a corresponding key, wherein the sub result is determined based on a comparison of the measurement unit and the decrypted template unit.

12. The system of claim 9 , wherein the processing device is further configured to:

responsive to determining that the measurement unit does not correspond to the template unit, send the measurement unit to a fourth node of the plurality of nodes.

13. The system of claim 9 ,

wherein to determine the sub-result of the plurality of sub results based on the comparison of the measurement unit to the template unit, the processing device is further configured to determine a distance between the measurement unit and the template unit, and

wherein the sub-result comprises an indication of the determined distance.

14. The system of claim 13 ,

wherein the measurement unit comprises a first vector coordinate of a first vector in Euclidian space and the template unit comprises a second vector coordinate of a second vector in the Euclidian space, and

wherein the determined distance is a distance between the first vector coordinate and the second vector coordinate in the Euclidian space.

15. The system of claim 14 ,

wherein the biometric measurement has been transformed using a machine learning model into the first vector comprising a first plurality of vector coordinates in the Euclidian space,

wherein the biometric template has been transformed using the machine learning model into the second vector comprising a second plurality of vector coordinates.

16. The system of claim 9 , wherein the first node is part of a decentralized network comprising the plurality of nodes, wherein the plurality of nodes are operated by different entities.

17. A method for authentication of a user comprising:

receiving, by a processing device, a measurement unit of a plurality of measurement units in response to a request to authenticate the user, wherein each of the plurality of measurement units received represents a less-than-complete portion of a complete biometric measurement provided by the user in conjunction with the request to authenticate the user;

determining whether the measurement unit corresponds to a template unit of a plurality of template units, wherein each of the plurality of template units represents a respective less-than-complete portion of a complete biometric template previously provided by the user, wherein the complete biometric template previously provided by the user represents a characteristic of the user that distinguishes the user from other users;

responsive to determining that the measurement unit corresponds to the template unit, determine a sub-result of a plurality of sub-results based on a comparison between the measurement unit and the template unit, wherein the sub-result indicates a level of similarity between the measurement unit and the template unit; and

sending the sub-result to a node of a plurality of nodes, wherein the authentication of the user is based at least in part on the sub-result.

18. The method of claim 17 , further comprising:

receiving, from a third node of the plurality of nodes, the template unit of the plurality of template units.

19. The method of claim 17 , wherein the template unit is an encrypted template unit, the method further comprising:

decrypting the encrypted template unit using a corresponding key, wherein the sub-result is determined based on a comparison of the measurement unit and the decrypted template unit.

20. The method of claim 17 , further comprising:

responsive to determining that the measurement unit does not correspond to the template unit, sending the measurement unit to a fourth node of the plurality of nodes.

21. The method of claim 17 ,

wherein determining the sub-result of the plurality of sub-results is based on the comparison of the measurement unit to the template unit,

wherein the method further comprises determining a distance between the measurement unit and the template unit, and

wherein the sub-result comprises an indication of the determined distance.

22. The method of claim 21 ,

wherein the measurement unit comprises a first vector coordinate of a first vector in Euclidian space and the template unit comprises a second vector coordinate of a second vector in the Euclidian space, and

wherein the determined distance is a distance between the first vector coordinate and the second vector coordinate in the Euclidian space,

wherein the biometric measurement has been transformed using a machine learning model into the first vector comprising a first plurality of vector coordinates in the Euclidian space,

wherein the biometric template has been transformed using the machine learning model into the second vector comprising a second plurality of vector coordinates.

23. A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:

receiving, by a processing device, a measurement unit of a plurality of measurement units in response to a request to authenticate a user, wherein each of the plurality of measurement units received represents less-than-complete portion of a complete biometric measurement provided by the user in conjunction with the request to authenticate the user;

determining whether the measurement unit corresponds to a template unit of a plurality of template units, wherein each of the plurality of template units represents a respective less-than-complete portion of a complete biometric template previously provided by the user, wherein the complete biometric template previously provided by the user represents a characteristic of the user that distinguishes the user from other users;

responsive to determining that the measurement unit corresponds to the template unit, determining a sub-result of a plurality of sub-results based on a comparison between the measurement unit and the template unit, wherein the sub-result indicates a level of similarity between the measurement unit and the template unit; and

sending the sub-result to a node of a plurality of nodes, wherein the authentication of the user is based at least in part on the sub-result.

24. The non-transitory computer-readable medium of claim 23 , wherein the template unit is an encrypted template unit, the operations further comprising:

decrypting the encrypted template unit using a corresponding key, wherein the sub-result is determined based on a comparison of the measurement unit and the decrypted template unit.

25. The non-transitory computer-readable medium of claim 23 ,

wherein determining the sub-result of the plurality of sub-results is based on the comparison of the measurement unit to the template unit,

the operations further comprising determining a distance between the measurement unit and the template unit,

wherein the sub-result comprises an indication of the determined distance.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2021
From: GOLDWERGER, EYAL S.; BULLKICH, ELAD; MITRANI, ERAN
To: ANONYBIT, INC.
Reel/Frame 055438/0880 →
Continuity (2)
Provisional Application 62726626 · Sep 4, 2018
Related Publication 20210342432A1 · Nov 4, 2021
References Cited (11)
US 6735695B1 · Gopalakrishnan et al. · 2004 [cited by applicant]
US 8239685B2 · Lee et al. · 2012 [cited by applicant]
US 8942429B2 · Le Saint · 2015 [cited by applicant]
US 20090113209A1 · Lee · 2009 [cited by examiner]
US 20110205020A1 · Le Saint · 2011 [cited by examiner]
US 20130339749A1 · Spuehier · 2013 [cited by examiner]
US 20140270408A1 · Hutchison, IV · 2014 [cited by examiner]
US 20160171280A1 · Han et al. · 2016 [cited by applicant]
Dasong Li, Image Semantic Transformation: Faster, Lighter, and Stronger, Mar. 27, 2018, Shanghai JiaoTong University, ZheJiang University (Year: 2018). [cited by examiner]
Li, D. and Wang, J., 2018. Image Semantic Transformation: Faster, Lighter and Stronger. arXiv preprint arXiv:1803.09932. [cited by applicant]
International Search Report and Written Opinion on Application No. PCT/US2019/049578, mailed on Nov. 12, 2019. [cited by applicant]