JPEG Compressed Images Can Bypass Protections Against AI Editing. (arXiv:2304.02234v1 [cs.LG])

Recently developed text-to-image diffusion models make it easy to edit or
create high-quality images. Their ease of use has raised concerns about the
potential for malicious editing or deepfake creation. Imperceptible
perturbations have been proposed as a means of protecting images from malicious
editing by preventing diffusion models from generating realistic images.
However, we find that the aforementioned perturbations are not robust to JPEG
compression, which poses a major weakness because of the common usage and
availability of JPEG. We …

availability bypass compression deepfake diffusion models discuss find high images jpeg major malicious protecting quality robustness text weakness