Method for authenticating a user of a mobile device

Patent metadata

Field	Value
Publication number	US-12475204-B2
Application number	US-202218565560-A
Country	US
Kind code	B2
Filing date	Jun 14, 2022
Priority date	Jun 15, 2021
Publication date	Nov 18, 2025
Grant date	Nov 18, 2025

Abstract

Disclosed herein is a method for authenticating a user of a mobile device. The method includes:
a) imaging at least one first image of a face by using at least one camera of the mobile device; b) providing the at least one first image to a regular execution environment of a processor of the mobile device and providing the at least one first image to a trusted execution environment of the processor; c) analyzing the at least one first image using at least one trained model in the regular execution environment thereby determining a multi-dimensional vector comprising image information; and d) a face verification step.

First claim

The invention claimed is:

1 . An authentication method for authenticating a user of a mobile device comprising the following steps:
a) imaging at least one first image of a face by using at least one camera of the mobile device; b) providing the at least one first image to a regular execution environment of a processor of the mobile device and providing the at least one first image to a trusted execution environment of the processor; c) analyzing the at least one first image using at least one trained model in the regular execution environment thereby determining a multi-dimensional vector comprising image information; and d) a face verification step comprising:
di) providing the multi-dimensional vector to the trusted execution environment;
dii) determining a second image from the multi-dimensional vector in the trusted execution environment by using at least one decoder;
diii) comparing the at least one first image and the second image, wherein in case the first image and the second image are identical the multi-dimensional vector is verified; and
div) in case the multi-dimensional vector is verified, the verified multi-dimensional vector is compared to a stored multi-dimensional vector of the user's face in the trusted execution environment, wherein in case the multi-dimensional vector and the stored multi-dimensional vector of the user's face are identical the user is authenticated.

2 . The authentication method according to claim 1 , wherein the trusted execution environment is an execution environment isolated from the regular execution environment.

3 . The authentication method according to claim 2 , wherein the trusted execution environment is isolated from the regular execution environment by one or more of physical isolation, hardware logic based isolation, and cryptographic isolation methods.

4 . The authentication method according to claim 1 , wherein the trusted execution environment comprises at least one security capability and fulfills at least one security requirement.

5 . The authentication method according to claim 1 , wherein the at least one first image is provided to the regular execution environment via a regular path, wherein the regular path is configured for allowing access by software within the regular execution environment and/or the trusted execution environment.

6 . The authentication method according to claim 1 , wherein the at least one first image is provided to the trusted execution environment via a secure path, wherein the secure path is configured for preventing the at least one first image to be derived and/or modified by any software within the regular execution environment.

7 . The authentication method according to claim 1 , wherein the determining of the second image comprises the decoder reconstructing the image of the user's face from the multi-dimensional vector.

8 . The authentication method according to claim 1 , wherein the trained model comprises at least one face recognition model.

9 . The authentication method according to claim 1 , wherein the trained model comprises at least one convolutional neural network.

10 . The authentication method according to claim 1 , wherein the analyzing in step c) comprises one or more of filtering and convoluting of the at least one first image.

11 . An authorization method for authorization of a user, wherein the authorization method comprises:
performing the authentication method according to claim 1 ; and outputting, by the trusted execution environment, a signal for authorizing a process step, wherein the process step comprises one or more of payment, signing of documents, access of the mobile device, and enabling applications.

12 . A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer or computer network, cause the computer or computer network to carry out the authentication method according to claim 1 .

13 . A mobile device comprising at least one camera and at least one processor, the mobile device being configured for performing the authentication method according to claim 1 .

14 . A method of using the mobile device according to claim 13 , the method comprising using the mobile device for one or more of payment and signing of documents.

15 . A non-transitory computer-readable storage medium comprising instructions which, when executed by a computer or computer network, cause the computer or computer network to carry out the authorization method according to claim 11 .

16 . A mobile device comprising at least one camera and at least one processor, the mobile device being configured for performing the authorization method according to claim 11 .

17 . A method of using the mobile device according to claim 16 , the method comprising using the mobile device for one or more of payment and signing of documents.

Assignees

• Trinamix Gmbh

Inventors

• Schick Friedrich
• Schillen Peter
• Guthier Benjamin
• Schindler Patrick
• Butov Dimitri
• Prediger Mark

Classifications

• G06F2221/2149

  Restricted operating environment · CPC title

• G06F21/53

  by executing in a restricted environment, e.g. sandbox or secure virtual machine · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V40/167

  using comparisons between temporally consecutive images · CPC title

• G06F2221/2105

  Dual mode as a secondary aspect · CPC title