# US 2025/0053865 A1 · Preventing The Distribution Of Forbidden Network Content With Robustified Detection

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

- Number: US 2025/0053865 A1
- Document ID: US20250053865A1
- Status: Published application
- Kind: A1
- Application number: 18/561,104
- Filed: 2022-12-14
- Published: 2025-02-13
- Earliest claimed: 2022-12-14
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Wei Qiao; Chun-Ta Lu; Yinatao Liu; Ariel Fuxman; Mehmet Nejat Tek; Dongjin Kwon; Florian Nils Stimberg
- Web page: https://patentgrep.com/patent/US20250053865A1

## CPC

- G06N 20/00: Machine learning
- G06N 3/02: Neural networks
- G06N 3/045: Combinations of networks
- G06N 3/08: Learning methods
- G06V 20/70: Labelling scene content, e.g. deriving syntactic or semantic representations
- H04L 63/1416: {Event detection, e.g. attack signature detection}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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

The technology is generally directed to the training and execution of a model to identify policy violating content that has been obfuscated. The model may be trained using obfuscated training images. The obfuscated training images may be associated with one or more labels, such as a policy, obfuscation label, etc. The obfuscated training images and associated labels may be input into the model. During training, the output of the model may be a policy prediction as to whether the obfuscated input images violate the content policy of a host or are approved content for publishing. During implementation, the model may receive content as input and provide as output a policy prediction for the content. The host may use the policy prediction provided by the model to determine whether or not to publish the content.

## Claims

### Claim 1

A method, comprising:
receiving as input to a machine learning model, by one or more processors, training images, wherein the training images includes at least one obfuscated training image;
associating, by the one or more processors, at least one label of a first set of labels to respective training images, wherein the first set of labels includes policy labels relating to a policy for approving content for publication; and
training, by the one or more processors based on the training images and the associated at least one label of the first set of labels, the machine learning model, wherein:
the machine learning model outputs policy predictions, and
the policy predictions include an indication of a violation or approval based on the respective policy labels.

### Claim 2 (depends on 1)

The method of claim 1, wherein the policy labels indicate a policy violation or a policy approval.

### Claim 3 (depends on 1)

The method of claim 1, further comprising associating, by the one or more processors, at least one label of a second set of labels to the respective training images, wherein the second set of labels includes obfuscation labels.

### Claim 4 (depends on 3)

The method of claim 3, wherein the obfuscation labels identify a type of obfuscation of a plurality of obfuscation types.

### Claim 5 (depends on 1)

The method of claim 1, further comprising executing the machine learning model to identify violative content, the executing comprising:
receiving one or more images as input into the machine learning model; and
determining, using the machine learning model, a policy prediction for each of the one or more images.

### Claim 6 (depends on 5)

The method of claim 5, wherein the policy prediction for each of the one or more images includes an indication of a violation or approval.

### Claim 7 (depends on 6)

The method of claim 6, wherein when the policy prediction includes the violation indication, the method further includes rejecting, by the one or more processors, the respective image such that the respective image is not provided for output.

### Claim 8 (depends on 6)

The method of claim 6, wherein when the policy prediction includes the approval indication, the method further includes providing for output, by the one or more processors, the respective image.

### Claim 9 (depends on 1)

The method of claim 1, further executing the machine learning model to identify violative content, the executing comprising detecting that the one or more images are one or more obfuscated images.

### Claim 10 (depends on 9)

The method of claim 9, further comprising detecting target concept of the one or more obfuscated images.

### Claim 11 (depends on 10)

The method of claim 10, further comprising comparing the detected target concept to a host's target concept.

### Claim 12

A system, comprising:
one or more processors, the one or more processors configured to:
receive as input to a machine learning model training images, wherein the training images includes at least one obfuscated training image;
associate at least one label of a first set of labels to respective training images, wherein the first set of labels includes policy labels relating to a policy for approving content for publication; and
train, based on the training images and the associated at least one label of the first set of labels, the machine learning model, wherein:
the machine learning model outputs policy predictions, and
the policy predictions include an indication of a violation or approval based on the respective policy labels.

### Claim 13 (depends on 12)

The system of claim 12, wherein the policy labels indicate a policy violation or a policy approval.

### Claim 14 (depends on 12)

The system of claim 12, wherein the one or more processors are further configured to associate at least one label of a second set of labels to the respective training images, wherein the second set of labels includes obfuscation labels.

### Claim 15 (depends on 14)

The system of claim 14, wherein the obfuscation labels identify a type of obfuscation of a plurality of obfuscation types.

### Claim 16 (depends on 15)

The system of claim 15, wherein the one or more processors are further configured to execute the machine learning model to identify violative content, the executing comprising:
receiving one or more images as input into the machine learning model; and
determining, using the machine learning model, a policy prediction for each of the one or more images.

### Claim 17 (depends on 16)

The system of claim 16, wherein the policy prediction for each of the one or more images includes an indication of a violation or approval.

### Claim 18 (depends on 17)

The system of claim 17, wherein when the policy prediction includes the violation indication, the one or more processors are further configured to reject the respective image such that the respective image is not provided for output.

### Claim 19 (depends on 17)

The system of claim 17, wherein when the policy prediction includes the approval indication, the one or more processors are further configured to provide for output the respective image.

### Claim 20

A non-transitory computer-readable medium storing instructions which, when executed by one or more processors, cause the one or more processors to:
receive as input to a machine learning model training images, wherein the training images includes at least one obfuscated training image;
associate at least one label of a first set of labels to respective training images, wherein the first set of labels includes policy labels relating to a policy for approving content for publication; and
train, based on the training images and the associated at least one label of the first set of labels, the machine learning model, wherein:
the machine learning model outputs policy predictions, and
the policy predictions include an indication of a violation or approval based on the respective policy labels.
