# US 2025/0158823 A1 · Facilitating authentication using stochastic-model-derived images

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

- Number: US 2025/0158823 A1
- Document ID: US20250158823A1
- Status: Published application
- Kind: A1
- Application number: 18/506,938
- Filed: 2023-11-10
- Published: 2025-05-15
- Earliest claimed: 2023-11-10
- Assignees: Capital One Services, LLC
- Applicants: Capital One Services, LLC
- Inventors: Tyler MAIMAN; Erik NEIGHBOUR
- Web page: https://patentgrep.com/patent/US20250158823A1

## CPC

- H04L 9/3213: {using tickets or tokens, e.g. Kerberos (network architectures or network communication protocols for entities authentication using tickets in a packet data network H04L63/0807)}
- G06F 21/36: by graphic or iconic representation
- G06N 3/047: Probabilistic or stochastic networks
- G06N 20/00: Machine learning
- G06T 11/00: Two-dimensional [2D] image generation
- H04L 63/0807: {using tickets, e.g. Kerberos (cryptographic mechanisms or cryptographic arrangements for entity authentication using tickets or tokens H04L9/3213)}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Methods and systems are described herein for facilitating token use authentication using stochastic-model-derived images. The system may detect an authentication request to authenticate use of an access token and retrieve operation data associated with the access token. The system may determine, based on the operation data, source data associated with a source of a network operation and alternative source data associated with an alternative source. The system may provide, to a stochastic machine learning model, the source data to obtain a first image for the network operation and the alternative source data to obtain a second image for the network operation. The system may then generate, for display, the first image and the second image and may receive a selection of the first image. Based on the selection of the first image, the system may grant the authentication request.

## Claims

### Claim 1

A system for facilitating token use authentication for an access token using stochastic-model-derived images generated using source data relating to a network operation performed using the access token, the system comprising:
one or more processors and one or more non-transitory, computer-readable media having computer-executable instructions stored thereon, the computer-executable instructions, when executed by the one or more processors, causing operations comprising:
detecting an authentication request to authenticate use of a network access token, the authentication request comprising a token identifier associated with the network access token;
in response to detecting the authentication request, retrieving, using the token identifier, operation data associated with the network access token;
determining, based on the operation data, source data associated with a source of a network operation and alternative source data associated with an alternative source, wherein the alternative source is different from the source;
generating, for input to a stochastic machine learning model, first image generation parameters using the source data associated with the source and second image generation parameters using the alternative source data associated with the alternative source;
providing, to the stochastic machine learning model, (i) the first image generation parameters to obtain a first stochastic image for the network operation and (ii) the second image generation parameters to obtain a second stochastic image for the network operation;
generating, for display, (i) an authentication image set comprising the first stochastic image and the second stochastic image and (ii) instructions to select an image associated with the source of the network operation; and
in response to a user image selection from the authentication image set, generating an authentication response to the authentication request such that the authentication response comprises (i) granting the authentication request in response to a first user selection of the first stochastic image and (ii) declining the authentication request in response to a second user selection of the second stochastic image.

### Claim 2

A method comprising:
detecting an authentication request to authenticate use of an access token, the authentication request comprising a token identifier associated with the access token;
retrieving, using the token identifier, operation data associated with the access token;
determining, based on the operation data, source data associated with a source of a network operation and alternative source data associated with an alternative source, wherein the alternative source is different from the source;
providing, to a stochastic machine learning model, (i) the source data to obtain a first image for the network operation and (ii) the alternative source data to obtain a second image for the network operation;
generating, for display, an image set comprising the first image and the second image;
receiving a selection of the first image from the image set; and
granting the authentication request based on the selection of the first image.

### Claim 3 (depends on 2)

The method of claim 2, further comprising generating, for display with the image set, instructions to select an image associated with the source of the network operation.

### Claim 4 (depends on 2)

The method of claim 2, further comprising declining the authentication request based on the selection of the second image.

### Claim 5 (depends on 2)

The method of claim 2, wherein providing the source data and the alternative source data to the stochastic machine learning model comprises:
generating, for input to the stochastic machine learning model, first image generation parameters using the source data associated with the source and second image generation parameters using the alternative source data associated with the alternative source; and
providing, to the stochastic machine learning model, (i) the first image generation parameters to obtain the first image and (ii) the second image generation parameters to obtain the second image.

### Claim 6 (depends on 5)

The method of claim 5, wherein the first image generation parameters comprise one or more first constraints for the first image and the second image generation parameters comprise one or more second constraints for the second image.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
determining, based on the operation data, a time associated with the source; and
determining the one or more first constraints based on the time associated with the source.

### Claim 8 (depends on 6)

The method of claim 6, further comprising:
determining, based on the operation data, a location associated with the source; and
determining the one or more first constraints based on the location associated with the source.

### Claim 9 (depends on 6)

The method of claim 6, further comprising:
determining, based on the operation data, a weather characteristic associated with the source; and
determining the one or more first constraints based on the weather characteristic associated with the source.

### Claim 10 (depends on 2)

The method of claim 2, wherein the source differs from the alternative source according to one or more of a time, a location, or a weather characteristic.

### Claim 11 (depends on 2)

The method of claim 2, wherein obtaining the second image comprises causing a generator of the stochastic machine learning model to generate the second image based on the alternative source data.

### Claim 12

One or more non-transitory, computer-readable media storing instructions that, when executed by one or more processors, cause operations comprising:
detecting an authentication request to authenticate access to an account, the authentication request comprising an account identifier associated with the account;
retrieving, using the account identifier, operation data associated with the account;
determining, based on the operation data, source data associated with a source of a network operation associated with the account and alternative source data associated with an alternative source, wherein the alternative source is different from the source;
obtaining, via one or more stochastic machine learning models, (i) a first image based on the source data and (ii) a second image based on the alternative source data;
generating, for display, an image set comprising the first image and the second image;
receiving a selection of the first image from the image set; and
granting the authentication request based on the selection of the first image.

### Claim 13 (depends on 12)

The one or more non-transitory, computer-readable media of claim 12, wherein the instructions further cause the one or more processors to perform operations comprising generating, for display with the image set, instructions to select an image associated with the source of the network operation.

### Claim 14 (depends on 12)

The one or more non-transitory, computer-readable media of claim 12, wherein the instructions further cause the one or more processors to perform operations comprising declining the authentication request based on the selection of the second image.

### Claim 15 (depends on 12)

The one or more non-transitory, computer-readable media of claim 12, wherein, to obtain, via the one or more stochastic machine learning models, the first image and the second image, the instructions further cause the one or more processors to perform operations comprising:
generating, for input to the one or more stochastic machine learning models, first image generation parameters using the source data associated with the source and second image generation parameters using the alternative source data associated with the alternative source; and
providing, to the one or more stochastic machine learning models, (i) the first image generation parameters to obtain the first image and (ii) the second image generation parameters to obtain the second image.

### Claim 16 (depends on 15)

The one or more non-transitory, computer-readable media of claim 15, wherein the first image generation parameters comprise one or more first constraints for the first image and the second image generation parameters comprise one or more second constraints for the second image.

### Claim 17 (depends on 16)

The one or more non-transitory, computer-readable media of claim 16, wherein the instructions further cause the one or more processors to perform operations comprising:
determining, based on the operation data, a time associated with the source; and
determining the one or more first constraints based on the time associated with the source.

### Claim 18 (depends on 16)

The one or more non-transitory, computer-readable media of claim 16, wherein the instructions further cause the one or more processors to perform operations comprising:
determining, based on the operation data, a location associated with the source; and
determining the one or more first constraints based on the location associated with the source.

### Claim 19 (depends on 16)

The one or more non-transitory, computer-readable media of claim 16, wherein the instructions further cause the one or more processors to perform operations comprising:
determining, based on the operation data, a weather characteristic associated with the source; and
determining the one or more first constraints based on the weather characteristic associated with the source.

### Claim 20 (depends on 12)

The one or more non-transitory, computer-readable media of claim 12, wherein, to obtain the second image, the instructions further cause the one or more processors to perform operations comprising causing a generator of the one or more stochastic machine learning models to generate the second image based on the alternative source data.
