My Art My Choice: Adversarial Protection Against Unruly AI

Anthony Rhodes, Ram Bhagat, Umur Aybars Ciftci, Ilke Demir; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 8389-8394

Generative AI is on the rise enabling everyone to produce realistic content via publicly available interfaces. Especially for guided image generation diffusion models are changing the creator economy by producing high-quality low-cost content. In parallel artists are rising against unruly AI since their artwork is leveraged distributed and dissimulated by large generative models. My Art My Choice (MAMC) aims to empower content owners by protecting their copyrighted materials from being utilized by diffusion models in an adversarial fashion. MAMC learns to generate adversarially perturbed "protected" versions of images which can in turn "break" diffusion models. The perturbation amount is decided by the artist to balance distortion vs. protection of the content. We experiment on four datasets both protected image and diffusion output results are evaluated in visual noise structure pixel and generative spaces.