Get the newsletter
Microsoft · AI / ML · Filed May 19, 2025 · USPTO published Nov 19, 2026 · This week's release

Microsoft Files Patent for Using AI to Hunt Down Images Its Search Filters Miss

Most image filters learn from pictures people have already searched for, so the worst material barely shows up in their training. Microsoft's patent application has an AI go looking for it on purpose.

AI creates targeted search queries to track down policy-violating photos and train a filter to block them in real-time results. Drawing from patent filing US 2026/0369038 A1.
AI creates targeted search queries to track down policy-violating photos and train a filter to block them in real-time results.All 10 drawings ↓
Publication number
US 2026/0369038 A1(US20260369038A1)
Applicant
Microsoft Technology Licensing, LLC
Filed · Published
May 19, 2025 · Nov 19, 2026
Inventors
Madhu RAMANATHAN, Ahmed Bahaaeldin MOHAMED, Sara Ahmed Mohamed ABDELGHAFFAR, Mohamed Farouk ABDELHADY
Status when we published
Examiner raised objections; the company can respond
Document
20 claims
US classification
382/224
Examiner
PERUNGAVOOR, SATHYANARAYA V (Art Unit 2488)

What Microsoft's image-moderation patent does

Imagine you search for a news photo and the results include something graphic, or a harmless picture gets blocked for no reason. Filters get these calls wrong partly because they learn from past searches, and truly bad images are rare in that pile, so the filter barely sees them.

Microsoft's patent application describes a fix. An AI reads the company's rules about which images are banned or restricted, then comes up with search terms that would turn up exactly those images. The results run through an image search, and anything that doesn't match the original idea gets thrown out.

The leftovers are mixed with a random sample of ordinary pictures and labeled by a second AI that can look at images. Those labels then teach a small, fast filter that screens results the moment you search.

From the filing · CLAIM 1
providing a search query generation prompt to a generative AI model to generate a set of image search queries from a regulated image policy, wherein the set of image search queries is used to identify images having a regulated image classification that is underrepresented in an image datastore; …

Translation: The system asks an AI to write search queries based on rules to find missing examples of banned images.

How the AI finds the pictures filters miss

The application covers a pipeline for building training data for an image filter. It starts with a written regulated image policy (the rules for what is banned for everyone or restricted for certain audiences). An AI model is prompted to brainstorm situations that would break the policy, then turn them into specific search terms.

Those terms go to an image search system, which returns a batch of pictures per term (the filing gives 100 as an example), with duplicates removed. Search results are messy, so each picture and each search term is converted into a vector embedding (a list of numbers that captures what something is about). A nearest-neighbor search (finding the closest matches) keeps pictures whose numbers sit near a term's numbers and drops the noise.

The kept pictures are combined with a random sample of everyday images from the existing catalog. Then a visual generative AI model (an AI that can look at an image and describe it) sorts each one using written guidelines, for example prohibited, restricted or permitted.

Finally, a small, fast classifier is trained on those labels and screens image results in real time. The filing says the big AI models do the slow prep work, sometimes during off-peak hours, because they are too slow and costly to check every search live.

From the filing · THE ABSTRACT
This disclosure describes a content moderation system that provides a multi-stage framework utilizing generative artificial intelligence (AI) models and vector-searching of multimodal embeddings to improve the accuracy and reliability of content moderation.

Translation: Microsoft patented an AI moderation system that uses advanced vector searches to catch filtered images.

Why faster image filters matter for search

If you search for images on any service, a filter behind the scenes decides what you see. Filters trained on past searches tend to see few examples of the worst content, so they let some through and block harmless pictures. The filing's own example is a mental health article whose neutral photos get tagged as restricted. Better training data could mean fewer of both mistakes.

The filing also says the approach can add examples of harmless pictures that are often wrongly flagged, such as open-backed dresses, and that it applies to content beyond images. The examiner's first review rejected the claims as filed, which is routine at this stage and usually followed by amendments.

This is the 30th Microsoft filing we've tracked since July in our AI guardrails race, following one on a filter for AI messages and one on self-checking AI coding help.

Source: US 2026/0369038 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Microsoft patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 10 sheets

10 drawing sheets from US 2026/0369038 A1 · click any drawing to enlarge

How AI trains a filter to catch banned search images, drawing sheet 1 from US 2026/0369038 A1
Sheet 1 How AI trains a filter to catch banned search images
Cloud servers that find prohibited images and train safety filters, drawing sheet 2 from US 2026/0369038 A1
Sheet 2 Cloud servers that find prohibited images and train safety filters
Three steps to build a training set of banned images, drawing sheet 3 from US 2026/0369038 A1
Sheet 3 Three steps to build a training set of banned images
Gathering candidate images using AI queries and a catalog sample, drawing sheet 4 from US 2026/0369038 A1
Sheet 4 Gathering candidate images using AI queries and a catalog sample
Picking out the most relevant banned pictures using search queries, drawing sheet 5 from US 2026/0369038 A1
Sheet 5 Picking out the most relevant banned pictures using search queries
Tagging training pictures with an AI visual inspection model, drawing sheet 6 from US 2026/0369038 A1
Sheet 6 Tagging training pictures with an AI visual inspection model
Training a quick search filter and using it live, drawing sheet 7 from US 2026/0369038 A1
Sheet 7 Training a quick search filter and using it live
Steps for creating training data to block prohibited search results, drawing sheet 8 from US 2026/0369038 A1
Sheet 8 Steps for creating training data to block prohibited search results
Show the other 2 sheets
Steps for labeling banned content to train safety filters, drawing sheet 9 from US 2026/0369038 A1
Sheet 9 Steps for labeling banned content to train safety filters
Computer hardware that runs the image moderation system, drawing sheet 10 from US 2026/0369038 A1
Sheet 10 Computer hardware that runs the image moderation system
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.