Detector for online user verification

Patent metadata

Field	Value
Publication number	US-2021349984-A1
Application number	US-202016866958-A
Country	US
Kind code	A1
Filing date	May 5, 2020
Priority date	May 5, 2020
Publication date	Nov 11, 2021
Grant date	—

Abstract

An approach is provided in which the approach provides a first question to a requestor requesting access to a resource. The first question corresponds to a first cognitive level and includes at least one image selected from a set of images. The approach computes a confidence value of a first answer received from the requestor responding to the first question. In response to determining that the confidence value is below a confidence threshold, the approach provides a second question to the requestor corresponding to a second cognitive level that is increased from the first cognitive level. The approach grants access to the requestor in response to determining that a second answer received from the requestor responding to the second question is a correct answer.

First claim

1 . A method implemented by an information handling system that includes a memory and a processor, the method comprising:
providing a first question to a requestor requesting access to a resource, wherein the first question corresponds to a first cognitive level and comprises at least one image selected from a plurality of images; computing a confidence level of a first answer received from the requestor responding to the first question; in response to determining that the confidence level is below a first confidence threshold, providing a second question to the requestor corresponding to a second cognitive level that is increased from the first cognitive level; and granting access of the resource to the requestor in response to determining that a second answer received from the requestor responding to the second question is a correct answer.

2 . The method of claim 1 further comprising:
selecting a first image from the plurality of images, wherein the first image is a real image that is unaltered;
injecting a set of distortion data into the first image to create a fake image, wherein the set of distortion data corresponds to a different image that is different from the real image, and wherein the fake image appears similar to the real image when viewed by a human; and
utilizing the fake image in the first question.

3 . The method of claim 2 further comprising:
generating a composite image by combining the fake image with a second image from the plurality of images; and
utilizing the composite image in the first question.

4 . The method of claim 2 further comprising:
prior to providing the first question to the requestor, generating a set of labels and a corresponding set of confidence values at the real image;
matching the first answer against one of the set of labels;
selecting one of the set of confidence values that corresponds to the matched label; and
utilizing the selected confidence value during the computing of the confidence level.

5 . The method of claim 2 further comprising:
prior to providing the first question to the requestor, generating a set of hints that correspond to the real image;
in response to determining that the confidence level of the first answer is below the first confidence threshold and above a second confidence threshold:
providing one of the set of hints to the requestor;
receiving a different first answer from the requestor in response to providing the hint to the requestor;
computing a different confidence level of the different first answer; and
granting the access of the resource to the requestor in response to determining that the different confidence level is above the first confidence threshold.

6 . The method of claim 5 further comprising:
in response to determining that the different confidence level of the first answer is below the first confidence threshold and above the second confidence threshold:
computing an amount of times that one of the set of hints has been provided to the requestor; and
rejecting the request to access the resource in response to determining that amount of times reaches a retry threshold.

7 . The method of claim 1 wherein the second question comprises a pattern recognition question.

8 . An information handling system comprising:
one or more processors; a memory coupled to at least one of the processors; a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions of:
providing a first question to a requestor requesting access to a resource, wherein the first question corresponds to a first cognitive level and comprises at least one image selected from a plurality of images;
computing a confidence level of a first answer received from the requestor responding to the first question;
in response to determining that the confidence level is below a first confidence threshold, providing a second question to the requestor corresponding to a second cognitive level that is increased from the first cognitive level; and
granting access of the resource to the requestor in response to determining that a second answer received from the requestor responding to the second question is a correct answer.

9 . The information handling system of claim 8 wherein the processors perform additional actions comprising:
selecting a first image from the plurality of images, wherein the first image is a real image that is unaltered;
injecting a set of distortion data into the first image to create a fake image, wherein the set of distortion data corresponds to a different image that is different from the real image, and wherein the fake image appears similar to the real image when viewed by a human; and
utilizing the fake image in the first question.

10 . The information handling system of claim 9 wherein the processors perform additional actions comprising:
generating a composite image by combining the fake image with a second image from the plurality of images; and
utilizing the composite image in the first question.

11 . The information handling system of claim 9 wherein the processors perform additional actions comprising:
prior to providing the first question to the requestor, generating a set of labels and a corresponding set of confidence values at the real image;
matching the first answer against one of the set of labels;
selecting one of the set of confidence values that corresponds to the matched label; and
utilizing the selected confidence value during the computing of the confidence level.

12 . The information handling system of claim 9 wherein the processors perform additional actions comprising:
prior to providing the first question to the requestor, generating a set of hints that correspond to the real image;
in response to determining that the confidence level of the first answer is below the first confidence threshold and above a second confidence threshold:
providing one of the set of hints to the requestor;
receiving a different first answer from the requestor in response to providing the hint to the requestor;
computing a different confidence level of the different first answer; and
granting the access of the resource to the requestor in response to determining that the different confidence level is above the first confidence threshold.

13 . The information handling system of claim 12 wherein the processors perform additional actions comprising:
in response to determining that the different confidence level of the first answer is below the first confidence threshold and above the second confidence threshold:
computing an amount of times that one of the set of hints has been provided to the requestor; and
rejecting the request to access the resource in response to determining that amount of times reaches a retry threshold.

14 . The information handling system of claim 8 wherein the second question comprises a pattern recognition question.

15 . A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, causes the information handling system to perform actions comprising:
providing a first question to a requestor requesting access to a resource, wherein the first question corresponds to a first cognitive level and comprises at least one image selected from a plurality of images; computing a confidence level of a first answer received from the requestor responding to the first question; in response to determining that the confidence level is below a first confidence threshold, provid

Assignees

• IBM

Inventors

• Ding Chengmin
• Vernier Stanley John
• Shek Elinna
• Decker Renee F

Classifications

• G06F21/36 Primary

  by graphic or iconic representation · CPC title

• G06Q50/265

  Personal security, identity or safety · CPC title

• G06T11/60

  Creating or editing images; Combining images with text · CPC title

• G06F2221/2103

  Challenge-response · CPC title