Deep Dive: How AI Text Watermarks Work
An AI text watermark leaves detectable evidence in the words a model chooses. During generation, a secret scoring rule helps select the next piece of text. Later, a detector with the matching key can reconstruct that rule and check whether the finished passage agrees with it unusually often.The…
An AI text watermark leaves detectable evidence in the words a model chooses. During generation, a secret scoring rule helps select the next piece of text. Later, a detector with the matching key can reconstruct that rule and check whether the finished passage agrees with it unusually often.The surprising part is that an exact copy into a plain-text document can preserve the evidence. There is no hidden character to carry along. The ordinary words preserve the choices.The dots are a detector overlay. Copying the same text preserves the inputs to that check.If you use AI to draft, proofread, or rewrite, the distinction matters: those operations leave different amounts of freedom for a watermark. And when someone says a passage was “detected,” the test matters too. A keyed watermark check measures a deliberately introduced pattern; it does not infer AI use from a writer's style. Read moreSource: The AI Edge — Published — Category: Research