Evaluating the Robustness of Text-to-image Diffusion Models against Real-world Attacks. (arXiv:2306.13103v1 [cs.CR])

Text-to-image (T2I) diffusion models (DMs) have shown promise in generating
high-quality images from textual descriptions. The real-world applications of
these models require particular attention to their safety and fidelity, but
this has not been sufficiently explored. One fundamental question is whether
existing T2I DMs are robust against variations over input texts. To answer it,
this work provides the first robustness evaluation of T2I DMs against
real-world attacks. Unlike prior studies that focus on malicious attacks
involving apocryphal alterations to the …

applications attacks attention descriptions diffusion models dms fidelity high images quality question robustness safety text world