DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing

TL;DR

DiffVax is a scalable, optimization-free image immunization framework that effectively prevents diffusion-based editing with minimal computational cost, generalizing well to unseen content and protecting videos.

Contribution

We introduce DiffVax, a novel, optimization-free approach that significantly reduces immunization time and enhances scalability against diffusion-based editing attacks.

Findings

Reduces immunization time from days to milliseconds

Achieves 250,000x speedup over previous methods

Effectively protects both images and videos from editing

Abstract

Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, 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 speedup of 250,000x. 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. More details are available in https://diffvax.github.io/ .