As AI developers indiscriminately suck up online content to train their models, artists are seeking ways to fight back.

Data poisoning: how artists are sabotaging AI to take revenge on image generators::As AI developers indiscriminately suck up online content to train their models, artists are seeking ways to fight back.

  • HejMedDig@feddit.dkEnglish
    161·
    11 months ago

    Let’s see how long before someone figures out how to poison, so it returns NSFW Images

    • daxnx01@lemmy.worldEnglish
      6·
      11 months ago

      You can create NSFW ai images already though?

      Or did you mean, when poisoned data is used a NSFW image is created instead of the expected image?

    • AVincentInSpace@pawb.socialEnglish
      4·
      11 months ago

      companies would stumble all over themselves to figure out how to get it to stop doing that before going live. source: they already are. see bing image generator appending “ethnically ambiguous” to every prompt it receives

      it would be a herculean if not impossible effort on the artists’ part only to watch the corpos scramble for max 2 weeks.

      when will you people learn that you cannot fight AI by trying to poison it. there is nothing you can do that horny weebs haven’t already done.

      • General_Effort@lemmy.worldEnglish
        3·
        11 months ago

        It can only target open source, so it wouldn’t bother corpos at all. The people behind this object to not everything being owned and controlled. That’s the whole point.

      • HejMedDig@feddit.dkEnglish
        1·
        11 months ago

        The Nightshade poisoning attack claims that it can corrupt a Stable Diffusion in less than 100 samples. Probably not to NSFW level. How easy it is to manufacture those 100 samples is not mentioned in the abstract

        • AVincentInSpace@pawb.socialEnglish
          2·
          11 months ago

          yeah the operative word in that sentence is “claims”

          I’d love nothing more than to be wrong, but after seeing how quickly Glaze got defeated (not only did it make the images nauseating for a human to look at despite claiming to be invisible, not even 48 hours after the official launch there was a neural network trained to reverse its effects automatically with like 95% accuracy), suffice to say my hopes aren’t high.