DeContext as Defense: Safe Image Editing in Diffusion Transformers

TL;DR

DeContext is a novel defense method that uses targeted perturbations to disrupt the attention pathways in diffusion transformers, preventing unauthorized image edits while maintaining image quality.

Contribution

The paper introduces DeContext, a simple yet effective technique to protect images from in-context editing by disrupting multimodal attention pathways in diffusion transformers.

Findings

DeContext effectively blocks unwanted image edits.

It preserves visual quality of images.

The method is efficient and robust against various attacks.

Abstract

In-context diffusion models allow users to modify images with remarkable ease and realism. However, the same power raises serious privacy concerns: personal images can be easily manipulated for identity impersonation, misinformation, or other malicious uses, all without the owner's consent. While prior work has explored input perturbations to protect against misuse in personalized text-to-image generation, the robustness of modern, large-scale in-context DiT-based models remains largely unexamined. In this paper, we propose DeContext, a new method to safeguard input images from unauthorized in-context editing. Our key insight is that contextual information from the source image propagates to the output primarily through multimodal attention layers. By injecting small, targeted perturbations that weaken these cross-attention pathways, DeContext breaks this flow, effectively decouples the link between input and output. This simple defense is both efficient and robust. We further show that early denoising steps and specific transformer blocks dominate context propagation, which allows us to concentrate perturbations where they matter most. Experiments on Flux Kontext and Step1X-Edit show that DeContext consistently blocks unwanted image edits while preserving visual quality. These results highlight the effectiveness of attention-based perturbations as a powerful defense against image manipulation. Code is available at https://github.com/LinghuiiShen/DeContext.