cross-posted from: https://midwest.social/post/14150726

But just as Glaze's userbase is spiking, a bigger priority for the Glaze Project has emerged: protecting users from attacks disabling Glaze's protections—including attack methods exposed in June by online security researchers in Zurich, Switzerland. In a paper published on Arxiv.org without peer review, the Zurich researchers, including Google DeepMind research scientist Nicholas Carlini, claimed that Glaze's protections could be "easily bypassed, leaving artists vulnerable to style mimicry."

  • peppersky [he/him, any]
    ·
    4 months ago

    The trick is to only draw extremely vulgar and obscene images that'd have to be filtered out of any dataset a company could possibly sell