Optimization-Free Image Immunization Against Diffusion-Based Editing
This addresses the problem of slow and computationally expensive defenses for users needing to protect images and videos from unauthorized editing, representing a significant improvement over prior methods.
The paper tackles the scalability issue of image immunization defenses against diffusion-based editing by introducing DiffVax, an optimization-free framework that reduces immunization time from days to milliseconds, achieving a 250,000x speedup while effectively protecting images and videos.
Current image immunization defense techniques against diffusion-based editing embed imperceptible noise in target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming re-optimization for each image-taking hours for small batches. To address these challenges, we introduce DiffVax, a scalable, lightweight, and optimization-free framework for image immunization, specifically designed to prevent diffusion-based editing. Our approach enables effective generalization to unseen content, reducing computational costs and cutting immunization time from days to milliseconds-achieving a 250,000x speedup. This is achieved through a loss term that ensures the failure of editing attempts and the imperceptibility of the perturbations. Extensive qualitative and quantitative results demonstrate that our model is scalable, optimization-free, adaptable to various diffusion-based editing tools, robust against counter-attacks, and, for the first time, effectively protects video content from editing. Our code is provided in our project webpage.