# US 2017/0318019 A1 · Gaze-based authentication

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0318019 A1
- Document ID: US20170318019A1
- Status: Published application
- Kind: A1
- Application number: 15/143,295
- Filed: 2016-04-29
- Published: 2017-11-02
- Earliest claimed: 2016-04-29
- Assignees: Microsoft Technology Licensing, LLC
- Inventors: John C. Gordon; Cem Keskin
- Web page: https://patentgrep.com/patent/US20170318019A1

## CPC

- G06F 21/36: by graphic or iconic representation
- G06F 3/013: {Eye tracking input arrangements (G06F3/015 takes precedence)}
- G06V 10/17: {using hand-held instruments}
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V 40/19: Sensors therefor
- G06V 40/197: {Matching; Classification}
- G06V 40/67: {by interactive indications to the user}
- H04L 9/3226: {using a predetermined code, e.g. password, passphrase or PIN (network architectures or network communication protocols for supporting authentication of entities using passwords in a packet data network H04L63/083)}
- H04L 63/083: {using passwords (cryptographic mechanisms or cryptographic arrangements for entity authentication using a predetermined code H04L9/3226)}
- H04L 63/102: {Entity profiles}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A user may be authenticated to access an account, computing device, or other resource using gaze tracking. A gaze-based password may be established by prompting a user to identify multiple gaze targets within a scene. The gaze-based password may be used to authenticate the user to access the resource. In some examples, when the user attempts to access the resource, the scene may be presented on a display. In some examples, the scene may be a real-world scene including the user's real-world surroundings, or a mixed reality scene. The user's gaze may be tracked while the user is viewing the scene to generate login gaze tracking data. The login gaze tracking data may be compared to the gaze-based password and, if the login gaze tracking data satisfies the gaze-based password, the user may be authenticated to access the resource.

## Claims

### Claim 1

A computing device comprising:
one or more processors; and
memory having computer-executable instructions stored thereupon which, when executed by the one or more processors, cause the computing device to perform operations comprising:
prompting a user to select, by looking at, multiple gaze targets within a scene;
obtaining, from a gaze tracking camera, gaze tracking data corresponding to gaze of the user responsive to the prompting;
identifying the multiple gaze targets within the scene based at least in part on the gaze tracking data; and
establishing, based at least in part on the multiple gaze targets, a gaze-based password usable to access a resource.

### Claim 2 (depends on 1)

The computing device of claim 1, the operations further comprising outputting feedback to visually identify the multiple gaze targets on a display.

### Claim 3 (depends on 1)

The computing device of claim 1, the operations further comprising:
prompting the user to visually confirm selection of the multiple gaze targets;
obtaining, from the gaze tracking camera, confirmation gaze tracking data visually confirming selection of the multiple gaze targets; and
establishing a margin for execution error based at least in part differences between the gaze tracking data and the confirmation gaze tracking data;
wherein the establishing the gaze-based password is further based at least in part on the margin for execution error.

### Claim 4 (depends on 1)

The computing device of claim 1, wherein the gaze-based password comprises a gaze glyph composed of the multiple gaze targets and one or more gaze paths between the multiple gaze targets.

### Claim 5 (depends on 1)

The computing device of claim 1, wherein the scene comprises a static image, and the multiple gaze targets correspond to objects depicted in the static image.

### Claim 6 (depends on 1)

The computing device of claim 1, wherein the scene comprises a computer generated scene, and the multiple gaze targets correspond to objects depicted in the computer generated scene.

### Claim 7 (depends on 1)

The computing device of claim 1, wherein the scene comprises multiple tiled images, and at least some of the multiple gaze targets comprise individual images of the multiple tiled images.

### Claim 8 (depends on 1)

The computing device of claim 1, wherein the scene comprises a real-world surrounding of the user, and the multiple gaze targets comprise physical objects in the real-world surrounding of the user.

### Claim 9 (depends on 1)

The computing device of claim 1, wherein the scene comprises a real-world surrounding of the user, and the multiple gaze targets comprise computer generated objects depicted in the real-world scene.

### Claim 10 (depends on 1)

The computing device of claim 1, the operations further comprising:
receiving a request to access the resource;
causing presentation of an authentication interface including the scene;
obtaining login gaze tracking data representing gaze of the user viewing the scene of the authentication interface;
comparing the login gaze tracking data to the gaze-based password usable to access the resource;
determining, based at least in part on the comparing, that the login gaze tracking data satisfies the gaze-based password; and
authenticating the user to access the resource based at least in part on the determining that the login gaze tracking data satisfies the gaze-based password.

### Claim 11

A computing device comprising:
one or more processors; and
memory having computer-executable instructions stored thereupon which, when executed by the one or more processors, cause the computing device to perform operations comprising:
causing presentation of multiple images on a display;
obtaining login gaze tracking data representing gaze of a user viewing the multiple images;
comparing the login gaze tracking data to a gaze-based password associated with an account;
determining, based at least in part on the comparing, that the login gaze tracking data satisfies the gaze-based password; and
authenticating the user to access the account based at least in part on the determining that the login gaze tracking data satisfies the gaze-based password.

### Claim 12 (depends on 11)

The computing device of claim 11, wherein:
the causing presentation of the multiple images comprises causing the multiple images to be presented concurrently in a tiled arrangement; and
the obtaining login gaze tracking data comprises obtaining gaze tracking data representing gaze of the user viewing at least a first gaze target in a first image of the multiple images and a second gaze target in a second image of the multiple images.

### Claim 13 (depends on 12)

The computing device of claim 12, wherein the obtaining login gaze tracking data further comprises obtaining gaze tracking data representing gaze of the user viewing at least a third gaze target in at least one of the first image of the multiple images or the second image of the multiple images.

### Claim 14 (depends on 11)

The computing device of claim 11, wherein:
the causing presentation of the multiple images comprises causing the multiple images to be presented concurrently within a scene; and
the obtaining login gaze tracking data comprises obtaining gaze tracking data representing gaze of the user viewing at least a first image of the multiple images and a second image of the multiple images.

### Claim 15 (depends on 11)

The computing device of claim 11, wherein:
the causing presentation of the multiple images comprises:
causing presentation of a first image; and
causing presentation of a second image; and
the obtaining login gaze tracking data comprises:
obtaining gaze tracking data representing gaze of the user viewing the first image; and
obtaining gaze tracking data representing gaze of the user viewing the second image.

### Claim 16

A computer-implemented method comprising:
obtaining, from an environmental camera, an image of a real-world scene;
obtaining, from a gaze tracking camera, gaze tracking data indicating multiple gaze targets, within the real-world scene, at which the user has gazed;
obtaining information about objects in the real-world scene corresponding to the multiple gaze targets; and
establishing, based at least in part on the information about the objects corresponding to the multiple gaze targets, a gaze-based password usable to access a resource.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein the information about the objects in the real-world scene comprise identifiers of the objects.

### Claim 18 (depends on 16)

The computer-implemented method of claim 16, further comprising:
receiving a request to access the resource;
obtaining login gaze tracking data representing gaze of the user during login;
comparing the login gaze tracking data to the gaze-based password usable to access the resource;
determining, based at least in part on the comparing, that the login gaze tracking data satisfies the gaze-based password; and
authenticating the user to access the resource based at least in part on the determining that the login gaze tracking data satisfies the gaze-based password.

### Claim 19 (depends on 18)

The computer-implemented method of claim 18, wherein:
the login gaze tracking data comprises information about objects in the real-world scene at which the user looked during login; and
the determining that the login gaze tracking data satisfies the gaze-based password comprises:
comparing the information about objects in the real-world scene at which the user looked during login with the information about the objects corresponding to the gaze targets; and
determining that the objects in the real-world scene at which the user looked during login are substantially the same as the objects corresponding to the gaze targets.

### Claim 20 (depends on 19)

The computer-implemented method of claim 19, wherein the determining that the login gaze tracking data satisfies the gaze-based password is independent of locations of the objects in the real-world scene at which the user looked during login.
