Re:To Watermark AI, It Needs Its Own Alphabet
by acroll on Thursday July 27, 2023 @12:22PM
(#36895943)
Also, you can use more robust models (like signing) to detect tampering; this is a markup approach for blended text; whether you trust the sender or not is another matter.
It would be fairly easy to undo, but the point is to create provenance for good actors, not fight bad ones.