Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection

TL;DR

This paper introduces a universal image immunization method that creates a single adversarial perturbation to prevent diffusion-based image editing, enhancing scalability and practicality in defending against malicious semantic manipulations.

Contribution

It presents the first universal immunization framework that generates a broad, effective adversarial perturbation for diffusion models without needing training data or domain knowledge.

Findings

Outperforms baseline methods in universal adversarial perturbation settings.

Achieves comparable results to image-specific methods under limited perturbation budgets.

Demonstrates strong black-box transferability across different diffusion models.

Abstract

Recent advances in diffusion models have enabled powerful image editing capabilities guided by natural language prompts, unlocking new creative possibilities. However, they introduce significant ethical and legal risks, such as deepfakes and unauthorized use of copyrighted visual content. To address these risks, image immunization has emerged as a promising defense against AI-driven semantic manipulation. Yet, most existing approaches rely on image-specific adversarial perturbations that require individual optimization for each image, thereby limiting scalability and practicality. In this paper, we propose the first universal image immunization framework that generates a single, broadly applicable adversarial perturbation specifically designed for diffusion-based editing pipelines. Inspired by universal adversarial perturbation (UAP) techniques used in targeted attacks, our method generates a UAP that embeds a semantic target into images to be protected. Simultaneously, it suppresses original content to effectively misdirect the model's attention during editing. As a result, our approach effectively blocks malicious editing attempts by overwriting the original semantic content in the image via the UAP. Moreover, our method operates effectively even in data-free settings without requiring access to training data or domain knowledge, further enhancing its practicality and broad applicability in real-world scenarios. Extensive experiments show that our method, as the first universal immunization approach, significantly outperforms several baselines in the UAP setting. In addition, despite the inherent difficulty of universal perturbations, our method also achieves performance on par with image-specific methods under a more restricted perturbation budget, while also exhibiting strong black-box transferability across different diffusion models.