My Art My Choice: Adversarial Protection Against Unruly AI

TL;DR

This paper introduces MAMC, a method that creates adversarially protected images to prevent diffusion models from copying copyrighted artwork, empowering artists to defend their creations against AI misuse.

Contribution

MAMC is a novel adversarial approach that generates protected images to specifically disrupt diffusion models, balancing content distortion and protection.

Findings

MAMC effectively breaks diffusion models in experiments.

Protected images retain visual similarity to original artworks.

The method adapts to various datasets and user control levels.

Abstract

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 are leveraged, distributed, and dissimulated by large generative models. Our approach, 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. MAMC is designed with a simple UNet-based generator, attacking black box diffusion models, combining several losses to create adversarial twins of the original artwork. We experiment on three datasets for various image-to-image tasks, with different user control values. Both protected image and diffusion output results are evaluated in visual, noise, structure, pixel, and generative spaces to validate our claims. We believe that MAMC is a crucial step for preserving ownership information for AI generated content in a flawless, based-on-need, and human-centric way.