Towards Transferable Defense Against Malicious Image Edits

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Jie, Dong, Shuai, Shan, Shiguang, Chen, Xilin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910037552660480
author Zhang, Jie
Dong, Shuai
Shan, Shiguang
Chen, Xilin
author_facet Zhang, Jie
Dong, Shuai
Shan, Shiguang
Chen, Xilin
contents Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we propose Transferable Defense Against Malicious Image Edits (TDAE), a novel bimodal framework that enhances image immunity against malicious edits through coordinated image-text optimization. Specifically, at the visual defense level, we introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective. By explicitly steering the perturbations toward flat minima, FDM amplifies immune robustness against unseen editing models. For textual enhancement protection, we propose an adversarial optimization paradigm named Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images, then updates the images under optimized embeddings. Through iterative adversarial updates to diverse embeddings, DPD enforces the generation of immunized images that seek a broader set of immunity-enhancing features, thereby achieving cross-model transferability. Extensive experimental results demonstrate that our TDAE achieves state-of-the-art performance in mitigating malicious edits under both intra- and cross-model evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_14341
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Transferable Defense Against Malicious Image Edits
Zhang, Jie
Dong, Shuai
Shan, Shiguang
Chen, Xilin
Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Machine Learning
Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited transferability in cross-model evaluations. To address this, we propose Transferable Defense Against Malicious Image Edits (TDAE), a novel bimodal framework that enhances image immunity against malicious edits through coordinated image-text optimization. Specifically, at the visual defense level, we introduce FlatGrad Defense Mechanism (FDM), which incorporates gradient regularization into the adversarial objective. By explicitly steering the perturbations toward flat minima, FDM amplifies immune robustness against unseen editing models. For textual enhancement protection, we propose an adversarial optimization paradigm named Dynamic Prompt Defense (DPD), which periodically refines text embeddings to align the editing outcomes of immunized images with those of the original images, then updates the images under optimized embeddings. Through iterative adversarial updates to diverse embeddings, DPD enforces the generation of immunized images that seek a broader set of immunity-enhancing features, thereby achieving cross-model transferability. Extensive experimental results demonstrate that our TDAE achieves state-of-the-art performance in mitigating malicious edits under both intra- and cross-model evaluations.
title Towards Transferable Defense Against Malicious Image Edits
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computers and Society
Machine Learning
url https://arxiv.org/abs/2512.14341