How does Fable 5.1 hide messages in images?

This seems very trivial... There are way more subtle and information dense ways to encode information in images.

Open an SVG in a text editor, check for data.

It may also be adding nodes to line art in specific patterns, think Morse Code.

Interesting, so this is nothing like the way OutGuess worked [1]. Though OutGuess worked with JPG images and these are apparently SVGs.

[1]: https://en.wikipedia.org/wiki/OutGuess

Here using images is incidental. In fact, what Fable is actually doing is generic encoding/decoding of a message into a medium. Ask it to hide a message in a poem and it should try to apply a strong (signal to noise ratio) family of schemes, for example quantized, margin-rich encoding. Robustness of features depends on the medium, so Fable is selecting strong encoding and robust features tailored to it.

But to be honest, images like these seem really strange, and even without this article I'd suspect something is encoded in building heights etc. Because normal image would never have such "weird" buildings. But nevertheless I guess it's able to encode message in even more subtle ways.

I think all AI models do that

Will be interesting to see agents intentionally hiding this stuff in a way operators can't spot from any human readable output or thinking trace, evading detection. Wonder if this has happened yet, but it seems inevitable.

Let's see if we can stego secret messages into SVG pelicans on bicycles, as a test.