Checked fact 4163 Oct 2026Safety and security
The paper lists limits: generative watermarks are vulnerable to stealing, spoofing and scrubbing attacks, and are weakened by edits to the text such as paraphrasing by a language model.
The exact words it rests on
Another limitation of generative watermarks is their vulnerability to stealing, spoofing and scrubbing attacks, which is an area of ongoing research. In particular, generative watermarks are weakened by edits to the text, such as through LLM paraphrasing
What the source said when we opened it, on 3 Oct 2026.
The source
Scalable watermarking for identifying large language model outputs
Checked
Checked by the notis newsroom on , against the source above.
In the story
How SynthID watermarks AI content and what limits it 3 Oct 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.