logoalt Hacker News

athrowaway3z • today at 6:33 PM • 1 reply • view on HN

>> Editing can weaken the watermark. In an evaluation of 400-token passages, replacing 10% of words with synonyms reduced detection from about 92% to 66%. Replacing 25% of words reduced it to 17%.

> Claude/codex/deepseek, please replace 25% of words with synonyms or slight rephrasing because i dont like the current version.

Not sure if that counts as: `a solution that's robust against "common alterations and adversarial attacks"`. Is there a sort of adversarial attack that is more common?


Replies

yorwba • today at 6:45 PM

If you use a watermarking model to do the synonym replacement, it will rephrase it in a way that is compatible with the watermark...