Raising the Cost of Malicious AI-Powered Image Editing
This addresses the risk of malicious image manipulation for users and organizations, though it is incremental as it builds on existing adversarial perturbation techniques.
The paper tackles the problem of malicious image editing by large diffusion models by immunizing images with imperceptible adversarial perturbations that disrupt these models, forcing them to generate unrealistic images, and demonstrates the efficacy of this approach.
We present an approach to mitigating the risks of malicious image editing posed by large diffusion models. The key idea is to immunize images so as to make them resistant to manipulation by these models. This immunization relies on injection of imperceptible adversarial perturbations designed to disrupt the operation of the targeted diffusion models, forcing them to generate unrealistic images. We provide two methods for crafting such perturbations, and then demonstrate their efficacy. Finally, we discuss a policy component necessary to make our approach fully effective and practical -- one that involves the organizations developing diffusion models, rather than individual users, to implement (and support) the immunization process.