AI Company Lets Cops Pinpoint Specific Houses Based on a Single Interior Photo

AI Company Lets Cops Pinpoint Specific Houses Based on a Single Interior Photo

Report

An AI company now lets cops take a photo and nearly instantly figure out what specific home it was taken in, using only clues in the photo itself, and is clearly pulling data from sites like Zillow and Airbnb.

Report

404 Media previously reported that both the Los Angeles Police Department and Miami-Dade Sheriff’s Office (MDSO) have bought access to Raven, which was previously called GeoSpy.

Report

Now, Raven, made by a company called Graylark Technologies, has added features that let cops analyze the interior of homes.

Report

In a post on LinkedIn earlier this month, Graylark CEO Daniel Heinen wrote the company was introducing “the ability to geolocate interior images across millions of short-term rental units worldwide.” An accompanying demo video shows someone taking a photo from X of a washer/dryer unit inside a building.

Report

They upload it to Raven, select “Find Property: Interior and exterior property geolocation,” and then choose a region to search.

Report

After a couple of seconds, the map interface zooms in on an area in Charlotte, North Carolina.

Report

On the right hand side, the screen displays a list of results.

Report

That result directly quotes the language on a specific Airbnb listing in Charlotte, and the photos in the Airbnb listing show the same property.

Report

Later in the video, the Raven user takes a photo of a bathroom from social media.

Report

They upload it to Raven, and the tool points to an area of Montecito, California.

Report

The top result says, “Montecito Miramar Beach House on the Sand.” 404 Media found that result directly quotes a listing on the short term rental site Vrbo.

Report

In other words, from a single photo, Raven appears to be able to quickly find the specific home it was taken in, without using location data or other metadata attached to the image.

Report

In the demonstrations the videos were from social media, but in practice they could be from anywhere a law enforcement officer has obtained them.

Report

This is also not a reverse image search: a reverse image search would take an image then find an identical one posted somewhere else on the internet.

Report

What Raven is doing, instead, is identifying unique characteristics in the photo, then finding what are likely other photos from the same property on sites like Airbnb, even if those photos are not exactly the same, or even if time has passed between them being taken.

Report

In another post, Heinen wrote, “For investigators working trafficking and exploitation cases, that connection can turn an unidentified room into a location lead they can verify and pursue.”

Report

Raven is not limited to short term rentals, according to other demo videos.

Report

In a third example posted last year, Raven traces a photo of an interior room to a specific address in San Francisco.

Report

The interface returns other interior photos of the property; 404 Media found these are exactly the same photos as those posted on Zillow, indicating that Raven is at least pulling data from Zillow in some form.

Report

Another video posted last week shows Raven identifying a particular hotel, too.

Report

In another video, a part of the interface says, “City-specific property AI to determine an address.” That phrase implies the property search isn’t necessarily worldwide, but dependent on an AI model built specifically for that city.

Report

When 404 Media reported earlier this year that at least two law enforcement agencies have bought access to Raven, emails showed the MDSO had access to a custom model specifically trained for Miami-Dade County.

Report

“In 2026, we’re investing heavily in interior geolocation across U.S. hotels, short-term rentals, houses, and apartments,” Heinen adds in the post.

Report

Graylark trained Raven on millions of images from around the world.

Report

When the tool first launched, it was focused on identifying distinct geographical markers like architecture and soil.

Report

Now Raven extends that same idea into buildings.

Report

In an interview with the tech publication Indicator last year, Heinen discussed some of how the building interior searching capability came to be.

Report

As we trained GeoSpy 2.0, we were just kind of red teaming and testing it out and I think I had a picture of my girlfriend just taking a selfie in the bathroom.

Report

It’s just a picture in a bathroom.’ And then I went over to Zillow and I just started screenshotting images and nine out of 10 of them it would get the right city.”

Report

“We have huge datasets that we train the models on and these are geotagged images from all over.

Report