Changeflow GovPing Telecom & Technology Detecting and Preventing Harmful Generative Ima...
Routine Notice Added Final

Detecting and Preventing Harmful Generative Image Outputs Using Digital Signatures

Email

Summary

The USPTO published patent application US20260111549A1 filed by inventors Meenaz Aliraza Merchant, Sudharsan Prabu, Kun Wu, and Surendra Ulabala on December 19, 2025. The application covers an image model protection system that uses digital signatures of identified harmful images to determine whether a particular harmful image was generated by a specific large generative image model. The system matches harmful images to generated outputs and identifies prompts used to create them, enabling security measures against similar harmful images in the future.

Published by USPTO on changeflow.com . Detected, standardized, and enriched by GovPing. Review our methodology and editorial standards .

About this source

USPTO classification G06N covers computer systems based on specific computational models: neural networks, knowledge representation, fuzzy logic, expert systems, evolutionary algorithms. With the AI patent boom, this is one of the most-filed application classes in the office. Every newly published application in G06N lands in this feed, around 230 a month. Patent applications publish 18 months after filing, so this feed reveals what AI labs and companies were working on in the prior year and a half. Watch this if you compete in machine learning, file freedom-to-operate analyses, scout acquisition targets in AI infrastructure, or track which research groups are converting publications to patents. GovPing pulls each application with the filing number, title, applicant, and abstract.

What changed

The USPTO published patent application US20260111549A1 for a system and method of detecting and preventing harmful generative image outputs using digital signatures. The image model protection system utilizes digital signatures of identified harmful images to determine whether a harmful image was generated by a specific large generative image model, matches the harmful image to model outputs, and identifies the prompt used to generate it. The system then uses the harmful prompt to implement new security measures. This publication represents a patent application, not a granted patent, and creates no compliance obligations for any party.

Archived snapshot

Apr 24, 2026

GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.

← USPTO Patent Applications

DETECTING AND PREVENTING HARMFUL GENERATIVE IMAGE OUTPUTSUSING DIGITALSIGNATURES

Application US20260111549A1 Kind: A1 Apr 23, 2026

Inventors

Meenaz Aliraza MERCHANT, Sudharsan PRABU, Kun WU, Surendra ULABALA

Abstract

This disclosure describes utilizing an image model protection system to improve the defensive robustness of a large generative image model against the generation of harmful digital images. For example, the image model protection system uses digital signatures of identified harmful images to determine whether a particular harmful image was generated by a specific large generative image model. Using digital signatures, the image model protection system matches the harmful image to images generated by the large generative image model. The image model protection system then identifies the prompt used to generate the image at the large generative image model. Furthermore, the image model protection system uses the harmful prompt to implement new security measures to safeguard the large generative image model against the generation of similar harmful images in the future.

CPC Classifications

G06F 21/566 G06F 21/554 G06N 3/0475 G06F 2221/034

Filing Date

2025-12-19

Application No.

19427582

View original document →

Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)

Daily digest delivered to your inbox.

Free. Unsubscribe anytime.

About this page

What is GovPing?

Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission

What's from the agency?

Source document text, dates, docket IDs, and authority are extracted directly from USPTO.

What's AI-generated?

The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.

Last updated

Classification

Agency
USPTO
Instrument
Notice
Branch
Executive
Legal weight
Non-binding
Stage
Final
Change scope
Minor

Who this affects

Applies to
Technology companies
Industry sector
5112 Software & Technology
Activity scope
Patent filing AI system development
Geographic scope
United States US

Taxonomy

Primary area
Intellectual Property
Operational domain
Legal
Topics
Artificial Intelligence

Get alerts for this source

We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.

Free. Unsubscribe anytime.

You're subscribed!