Study exposes failings of measures to prevent illegal content generation by text-to-image AI models

Researchers at NYU Tandon School of Engineering have revealed critical shortcomings in recently-proposed methods aimed at making powerful text-to-image generative AI systems safer for public use.

ai models ai systems content generation engineering generative image making nyu nyu tandon public researchers school school of engineering security study systems text text-to-image text-to-image ai