How AI text watermarking works
declaude.org
A gentle visual guide to how a statistical mark hides inside generated text, and what erases it.
  • antianarchist@sopuli.xyzEnglish
    71·
    13 days ago
    • Only the key-holder can check. Your teacher, editor, or favourite “AI detector” website cannot run this test; a genuine check needs the provider’s secret key, or a checking service the provider runs. Google runs an early-access detector portal for SynthID; Anthropic says detection tooling is forthcoming.

    I am not so sure about that. The amounts of words is finite and with enough text, you will see that certain words are used more often, especially in certain combinations. I believe people will brute force this and then create a way to destroy the watermark again.

    • trem@lemmy.blahaj.zoneEnglish
      2·
      13 days ago

      Yeah, they can’t easily rotate keys, because the text can’t tell you which key was used.

      They could switch to a new key e.g. every month and then just check every previous key during detection. But that would slowly increase the likelihood of false positives, so no idea if that’s a good idea either.

    • Zacryon@feddit.orgEnglish
      1·
      13 days ago

      with enough text, you will see that certain words are used more often

      Which is also a thing humans do.

      • antianarchist@sopuli.xyzEnglish
        2·
        13 days ago

        Absolutely! We all basically do fingerprinting. We’re just not really conscious about the key we are using. But with a bit of statistics, you could identify people.

        • Zacryon@feddit.orgEnglish
          2·
          12 days ago

          But how reliable? With which guarantees? What are the prerequisites for this to work at all? Telling people from each other apart is one thing, the other is telling them reliably apart from a machine generated text.