System, device, and method of secure utilization of fingerprints for user authentication

• US 10,579,784 B2
• Filed: 08/13/2017
• Issued: 03/03/2020
• Est. Priority Date: 11/02/2016
• Status: Active Grant

• Current Assignee: Biocatch Ltd.
• Original Assignee: Biocatch Ltd.
• Inventors: Turgeman, Avi
• Primary Examiner(s): Li, Ruiping
• Application Number:
  US15/675,740
• Publication Number:
  US 20180121640A1
• Time in Patent Office: 933 Days
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 2203/0338 Fingerprint track pad, i.e. fingerprint sensor used as pointing device tracking the fingertip image
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0488 using a touch-screen or digitiser, e.g. input of commands through traced gestures
• CPC Class Codes: G06V 40/13 Sensors therefor
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16

Abstract

System, device, and method of secure utilization of fingerprints for user authentication. A method includes: capturing a fingerprint that a particular user provides to an electronic device; generating a raw fingerprint signature that corresponds to bodily features of the fingerprint of the particular user; monitoring user interactions of the particular user, during the capturing of the raw fingerprint, via one or more input units of the electronic device; extracting from the monitored user interactions a user-specific characteristic that is user-specific to the interactions of the particular user; generating a user-specific reference fused data-item, by utilizing both: (I) the raw fingerprint signature that was generated, and (II) the user-specific characteristic that was extracted; subsequently, utilizing the reference fused data-item as a reference for user-authentication.

Claims

1. A method comprising:

(a) capturing a fingerprint that a particular user provides to an electronic device during a first usage-session of said particular user with said electronic device; and

generating a raw fingerprint signature that corresponds to bodily features of the fingerprint of said particular user;

wherein said capturing is performed by a first input unit of said electronic device, the first input unit being a fingerprint scanning unit of said electronic device;

(b) monitoring user interactions of said particular user, during a second, different, usage-session of said particular user with said electronic device, via a second, different, input unit of said electronic device, wherein said monitoring is performed by said second input unit which is an input unit selected from the group consisting of;

accelerometer, gyroscope, device spatial-orientation sensor; and

extracting from said user interactions a user-specific behavioral characteristic that is specific to the interactions of said particular user with said electronic device;

(c) generating a user-specific reference fused data-item, by hashing together;

(I) the raw fingerprint signature that was generated in step (a) based on the fingerprint as scanned by said first input unit during said first usage-session, and (II) the user-specific behavioral characteristic that was extracted in step (b) based on user interactions monitored via said second input unit during said second usage-session;

(d) subsequently, utilizing said reference fused data-item that was generated in step (c), as a reference value for user-authentication of said particular user.

2. The method of claim 1, wherein the monitoring of step (b) is performed non-concurrently with the capturing of step (a).

3. The method of claim 1, wherein the monitoring of step (b) is performed at least T minutes prior to the capturing of step (a), wherein T is a pre-defined value.

4. The method of claim 1, wherein the monitoring of step (b) is performed at least T minutes after the capturing of step (a), wherein T is a pre-defined value.

5. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates a user-specific manner of behavior of said particular user when said particular user utilizes the electronic device to perform operations other than capturing said fingerprint.

6. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates that said particular user performs a particular slanting of said electronic device when said particular user utilizes the electronic device.

7. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates that said particular user performs a particular tilting of said electronic device when said particular user utilizes the electronic device.

8. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates that said particular user performs a particular rotating of said electronic device when said particular user utilizes the electronic device.

9. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates that said particular user performs a particular accelerated movement of said electronic device when said particular user utilizes the electronic device.

10. The method of claim 1, wherein generating the user-specific fused data item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a user-specific behavioral characteristic that indicates that said particular user performs a particular device-orientation movement of said electronic device when said particular user utilizes the electronic device.

11. The method of claim 1, comprising:

subsequently, capturing a fresh raw fingerprint and fresh user-interactions, and generating a fresh fused data-item that is based on both (i) the fresh raw fingerprint, and (ii) a fresh user-specific characteristic extracted from the fresh user-interactions;

authenticating a user by comparing the fresh fused data-item to said reference fused data-item.

12. The method of claim 1, comprising:

subsequently, capturing a fresh raw fingerprint and fresh user-interactions, and generating a fresh fused data-item that is based on both (i) the fresh raw fingerprint, and (ii) a fresh user-specific characteristic extracted from the fresh user-interactions;

comparing the fresh fused data-item to said reference fused data-item;

if the fresh fused data-item matches said reference fused data-item, then authorizing access of the user to a computerized service;

if the fresh fused data-item does not match said reference fused data-item, then blocking access of the user to said computerized service.

13. The method of claim 1, wherein generating the reference fused data-item is performed by utilizing at least:

(I) the raw fingerprint signature that was generated in step (a), and (II) a set of two different user-specific characteristics that are extracted from user interactions that are monitored across at least two separate usage-sessions.

14. The method of claim 1, comprising:

subsequently, receiving an indication that said reference fused data-item was compromised;

discarding said reference fused data-item;

generating a replacement reference fused data-item, based on both;

(I) the raw fingerprint signature that was generated in step (a) during the first usage-session, and a different user-specific characteristic that is extracted from user interactions during said second usage-session or during another, third, user session.

15. The method of claim 1, wherein step (d) comprises:

authenticating said particular user based on said reference fused data-item as a reference, without performing any comparison between (i) the raw fingerprint that was captured in step (a), and (ii) a freshly-captured raw fingerprint.

16. The method of claim 1, wherein step (d) comprises:

authenticating said particular user based on said reference fused data-item as a reference, without performing any comparison between (i) a hashed value of the raw fingerprint that was captured in step (a), and (ii) a hashed value of a freshly-captured raw fingerprint.

17. The method of claim 1, wherein the step of generating the reference fused data-item comprises:

generating the reference fused data-item by utilizing a function that receives as input both;

(I) the raw fingerprint signature that was generated in step (a), and (II) the user-specific characteristic that was extracted in step (b) from a sensed device-acceleration value that was sensed by an accelerometer of said electronic device.

18. The method of claim 1, wherein the step of generating the reference fused data-item comprises:

generating the reference fused data-item by utilizing a function that receives as input both;

(I) the raw fingerprint signature that was generated in step (a) during said first usage-session, and (II) the user-specific characteristic that was extracted in step (b) from a sensed device-orientation value that was sensed by one or more gyroscopes of said electronic device during said second usage-session.

19. The method of claim 1, wherein the step of generating the reference fused data-item comprises:

generating the reference fused data-item by utilizing a function that receives as input at least;

(I) the raw fingerprint signature that was generated in step (a) during said first usage-session, and also

(II) a first user-specific characteristic that was extracted in step (b) from a sensed device-acceleration value that was sensed by an accelerometer of said electronic device during said second usage-session, and also

(III) a second user-specific characteristic that was extracted in step (b) from a sensed device-orientation value that was sensed by one or more gyroscopes of said electronic device during said second usage session.

20. A process comprising:

(a) capturing a fingerprint that a particular user provides to an electronic device during a first usage-session of said particular user with said electronic device; and

generating a raw fingerprint signature that corresponds to bodily features of the fingerprint of said particular user;

wherein said capturing is performed by a first input unit of said electronic device, the first input unit being a fingerprint scanning unit of said electronic device; and

generating a hashed value of said raw fingerprint signature;

(b) monitoring user interactions of said particular user, during a second, different, usage-session of said particular user with said electronic device, via a second, different, input unit of said electronic device, wherein said monitoring is performed by said second input unit which is an input unit selected from the group consisting of;

accelerometer, gyroscope, device spatial-orientation sensor; and

extracting from said user interactions a user-specific behavioral characteristic that is specific to the interactions of said particular user with said electronic device; and

generating a hashed value of said user-specific behavioral characteristic;

(c) generating a user-specific reference fused data-item, by hashing together;

(I) the hashed value of the raw fingerprint signature that was generated in step (a) based on the fingerprint as scanned by said first input unit during said first usage-session, and (II) the hashed value of the user-specific behavioral characteristic that was extracted in step (b) based on user interactions monitored via said second input unit during said second usage-session;

(d) subsequently, utilizing said reference fused data-item that was generated in step (c), as a reference value for user-authentication of said particular user.