JPEG Compressed Images Can Bypass Protections Against AI Editing
This exposes a critical weakness in current image protection methods, posing a problem for security applications against malicious editing.
The paper tackles the vulnerability of imperceptible perturbations designed to protect images from AI editing, showing they are not robust to JPEG compression, a widely used format.
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 discuss the importance of robustness for additive imperceptible perturbations and encourage alternative approaches to protect images against editing.