IP Library Granted Patent US 12,244,590
Granted Patent B2
US 12,244,590 · App. 17/997,081 · Granted Mar 4, 2025

Access authentication using obfuscated biometrics

Inventors: Johannes Lutz Schonberger (Zurich, CH); Marc Andre Leon Pollefeys (Zurich, CH)
Assignee: Microsoft Technology Licensing, LLC
H04L63/0861H04L63/10H04L9/3231
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 12,244,590
App. No.
17/997,081
Granted
Mar 4, 2025
Kind
B2
Abstract

A method for authorizing access to one or more secured computer resources includes obfuscating a reference biometric vector into an obfuscated reference biometric vector using a similarity-preserving obfuscation. An authentication biometric vector is obfuscated into an obfuscated authentication biometric vector using the similarity-preserving obfuscation. A similarity of the obfuscated authentication biometric vector and the obfuscated reference biometric vector is tested. Based on the similarity being within an authentication threshold, access to the one or more secured computer resources is authorized.

Claims (31)

1. A method for authorizing access to one or more secured computer resources, the method comprising:

storing an obfuscated reference biometric vector at an authentication computing device, the obfuscated reference biometric vector previously obfuscated from a reference biometric vector using a similarity-preserving obfuscation at a client computing device, wherein the reference biometric vector includes N dimensions, wherein the similarity-preserving obfuscation is a deterministic vector rotation in which a sequence of rotations is applied relative to one or more of the N dimensions, and wherein the sequence of rotations is generated based on a seed value;

receiving an obfuscated authentication biometric vector, the obfuscated authentication biometric vector previously obfuscated from an authentication biometric vector using the similarity-preserving obfuscation at the client computing device;

testing a similarity of the obfuscated reference biometric vector and the obfuscated authentication biometric vector at the authentication computing device; and

based on the similarity being within an authentication threshold, communicating an authentication authorization from the authentication computing device to the client computing device to grant access to the one or more secured computer resources,

wherein the similarity-preserving obfuscation uses a received authentication credential as the seed value for a random number generator to generate the sequence of rotations.

2. The method of claim 1 , wherein testing the similarity of the obfuscated reference biometric vector and the obfuscated authentication biometric vector includes calculating a cosine angular distance between the obfuscated reference biometric vector and the obfuscated authentication biometric vector.

3. The method of claim 1 , wherein testing the similarity of the obfuscated reference biometric vector and the obfuscated authentication biometric vector includes calculating an L2 norm between the obfuscated reference biometric vector and the obfuscated authentication biometric vector.

4. The method of claim 1 , wherein the received authentication credential is a password.

5. The method of claim 1 , wherein the received authentication credential is a device identifier.

6. The method of claim 1 , wherein the received authentication credential is a biometric identifier.

7. A method of granting access to one or more secured computer resources, the method comprising:

obfuscating a reference biometric vector into an obfuscated reference biometric vector using a similarity-preserving obfuscation at a client computing device, wherein the reference biometric vector includes N dimensions, wherein the similarity-preserving obfuscation is a deterministic vector rotation in which a sequence of rotations is applied relative to one or more of the N dimensions, and wherein the sequence of rotations is generated based on a seed value;

sending the obfuscated reference biometric vector from the client computing device to an authentication computing device;

measuring an authentication biometric identifier at the client computing device;

transforming the authentication biometric identifier into an authentication biometric vector at the client computing device;

obfuscating the authentication biometric vector into an obfuscated authentication biometric vector using the similarity-preserving obfuscation at the client computing device;

sending the obfuscated authentication biometric vector from the client computing device to the authentication computing device; and

based on receiving an authentication authorization from the authentication computing device, granting access to the one or more secured computer resources, the authentication authorization previously determined at the authentication computing device based on a similarity of the obfuscated reference biometric vector and the obfuscated authentication biometric vector being within an authentication threshold,

wherein the similarity-preserving obfuscation uses a received authentication credential as the seed value for a random number generator to generate the sequence of rotations.

8. The method of claim 7 , wherein the reference biometric vector is transformed from a reference biometric identifier measured at the client computing device.

9. The method of claim 7 , wherein the authentication biometric identifier is a sensed human fingerprint.

10. The method of claim 7 , wherein the authentication biometric identifier is a sensed human iris.

11. The method of claim 7 , wherein the authentication biometric identifier is a sensed human face.

12. The method of claim 7 , wherein the authentication biometric identifier is a sensed human voice.

13. A method of authorizing access to one or more secured computer resources, the method comprising:

obfuscating a reference biometric vector into an obfuscated reference biometric vector using a similarity-preserving obfuscation, wherein the reference biometric vector includes N dimensions, wherein the similarity-preserving obfuscation is a deterministic vector rotation in which a sequence of rotations is applied relative to one or more of the N dimensions, and wherein the sequence of rotations is generated based on a seed value;

obfuscating an authentication biometric vector into an obfuscated authentication biometric vector using the similarity-preserving obfuscation;

testing a similarity of the obfuscated authentication biometric vector and the obfuscated reference biometric vector; and

based on the similarity being within an authentication threshold, authorizing access to the one or more secured computer resources,

wherein the similarity-preserving obfuscation uses a received authentication credential as the seed value for a random number generator to generate the sequence of rotations.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 25, 2022
From: SCHONBERGER, JOHANNES LUTZ; POLLEFEYS, MARC ANDRE LEON
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 061530/0853 →
Priority Claims (1)
NL 2025515 · May 6, 2020 · national
Continuity (1)
Related Publication 20230179596A1 · Jun 8, 2023
References Cited (38)
US 8842887B2 · Beatson et al. · 2014 [cited by applicant]
US 8972742B2 · Troncoso Pastoriza et al. · 2015 [cited by applicant]
US 9665704B2 · Beatson et al. · 2017 [cited by applicant]
US 9838388B2 · Mather et al. · 2017 [cited by applicant]
US 9888382B2 · Chung et al. · 2018 [cited by applicant]
US 11418319B2 · Aharoni · 2022 [cited by examiner]
US 11777736B2 · Blackhurst · 2023 [cited by examiner]
US 20110037563A1 · Choi et al. · 2011 [cited by applicant]
US 20150186721A1 · Derakhshani · 2015 [cited by applicant]
US 20150379250A1 · Saito et al. · 2015 [cited by applicant]
US 20160119119A1 · Calapodescu · 2016 [cited by examiner]
US 20190280868A1 · Streit · 2019 [cited by applicant]
US 20200036749A1 · Ferres et al. · 2020 [cited by applicant]
US 20200050794A1 · Hassan et al. · 2020 [cited by applicant]
US 20200349247A1 · Seo · 2020 [cited by examiner]
US 20210342432A1 · Goldwerger · 2021 [cited by examiner]
US 20230370251A1 · Ikarashi · 2023 [cited by examiner]
CN 108475309A · 2018 [cited by applicant]
EP 1706957B1 · 2018 [cited by applicant]
JP 2006158851A · 2006 [cited by applicant]
JP 2008129743A · 2008 [cited by applicant]
JP 2010034967A · 2010 [cited by applicant]
JP 2016114692A · 2016 [cited by applicant]
RU 2386220C2 · 2010 [cited by applicant]
WO 2019032301A1 · 2019 [cited by applicant]
Abidin, Aysajan, “On Privacy-Preserving Biometric Authentication”, In Proceedings of International Conference on Information Security and Cryptology, Mar. 3, 2017, pp. 169-186. [cited by applicant]
Chun, et al., “Outsourceable Two-Party Privacy-Preserving Biometric Authentication”, In Proceedings of the 9th ACM Symposium on Information, Computer and Communications Security, Jun. 4, 2014, pp. 401-412. [cited by applicant]
Lagendijk, et al., “Encrypted Signal Processing for Privacy Protection: Conveying the utility of homomorphic encryption and multiparty computation”, In Journal of IEEE Signal Processing Magazine, vol. 30, Issue 1, Jan. … [cited by applicant]
Maneesh, et al., “Efficient Biometric Verification in Encrypted Domain”, In Book of International Conference on Biometrics, Jun. 2, 2009, pp. 899-908. [cited by applicant]
“Search Report and Written Opinion Issued in Netherlands Patent Application No. N2025515”, Mailed Date: Feb. 19, 2021, 11 Pages. [cited by applicant]
“International Search Report and Written Opinion Issued in PCT Application No. PCT/US21/070439”, Mailed Date: Aug. 13, 2021, 12 Pages. [cited by applicant]
Wang, et al., “An Analysis of Random Projection for Changeable and Privacy-Preserving Biometric Verification”, In Journal of IEEE Transactions on Systems, Man, and Cybernetics, Part B Cybernetics, vol. 40, Issue 5, Oct.… [cited by applicant]
Zhmoginov, et al., “Inverting face embeddings with convolutional neural networks”, In Repository of arXiv: 1606.04189v2, Jul. 7, 2016, pp. 1-12. [cited by applicant]
Decision to Grant Received for Chinese Application No. 202180033165.7, mailed on Jul. 26, 2024, 04 pages (English Translation Provided). [cited by applicant]
First Office Action Received for Chinese Application No. 202180033165.7, mailed on Jun. 6, 2024, 8 pages. (English Translation Provided). [cited by applicant]
Gottemukkula, et al., “Enhanced Obfuscation for Multi-part Biometric Templates”, IEEE Congress on Evolutionary Computation (CEC), Jul. 29, 2016, pp. 1394-1401. [cited by applicant]
Office Action Received for Russian Application No. 2022130824 mailed on Aug. 7, 2024, 22 pages. (English translation Provided). [cited by applicant]
Notice of reasons for refusal Received for Japanese Application No. 2022-560884, mailed on Dec. 19, 2024, 4 pages. [cited by applicant]