• uis@lemm.ee
    link
    fedilink
    English
    arrow-up
    2
    ·
    1 month ago

    Reminds me of how artists are starting to embed data and metadata in their pieces that fuck up AI training data.

    It still trains AI. Even adding noise does. Remember captchas?

    Metadata… unlikely to do anything.

    • Phoenix3875@lemmy.world
      link
      fedilink
      English
      arrow-up
      2
      ·
      1 month ago

      In theory, methods like nightshades are supposed to poison the work such that AI systems trained on them will have their performance degraded significantly.

      • uis@lemm.ee
        link
        fedilink
        English
        arrow-up
        1
        ·
        edit-2
        1 month ago

        Read it. I don’t think it will have bigger impact than lossy image compression or noisy raytraced images.

      • lemmysarius@feddit.org
        link
        fedilink
        English
        arrow-up
        1
        ·
        1 month ago

        The problem with nightshade or similar tools is, that if you leave the changes it makes at too weak a setting, then it can be pretty easily removed. For example GAN upscalers that pre date modern “AI”, were pretty much built to remove noise or foreign patterns. And if you make the changes strong enough that they can’t be removed by these models (because so much information was lost), then the image looks like shit. Its really difficult to strike a balance here.