Towards More Realistic Membership Inference Attacks on Large Diffusion Models. (arXiv:2306.12983v1 [cs.LG])

Generative diffusion models, including Stable Diffusion and Midjourney, can
generate visually appealing, diverse, and high-resolution images for various
applications. These models are trained on billions of internet-sourced images,
raising significant concerns about the potential unauthorized use of
copyright-protected images. In this paper, we examine whether it is possible to
determine if a specific image was used in the training set, a problem known in
the cybersecurity community and referred to as a membership inference attack.
Our focus is on Stable …

applications attacks copyright diffusion models generative high images internet large midjourney resolution stable diffusion