Swap 10% of the words and
@OpenAI's watermark detection drops from 92% to 66%.
Edit the text, lose the proof.
Our model fingerprinting puts the mark in the weights, where a thesaurus can't reach it.
Watermarks have limits. They’re often undetectable, especially in short passages. Rewriting or translating text can completely remove the watermark.
That’s why, for now, only approved researchers will have access to our detector, so they can help us evaluate and improve the technology.
We’re treating text watermarking as an ongoing area of research. We’ll keep testing and improving, with feedback from users, developers, policymakers, and researchers.
더 보기