Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.13711 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918142591107072 |
|---|---|
| author | Tang, Qiuyu Krinsky, Joshua Bharati, Aparna |
| author_facet | Tang, Qiuyu Krinsky, Joshua Bharati, Aparna |
| contents | The rapid advancement of generative models, particularly diffusion-based approaches, has inadvertently facilitated their potential for misuse. Such models enable malicious exploiters to replicate artistic styles that capture an artist's creative labor, personal vision, and years of dedication in an inexpensive manner. This has led to a rise in the need and exploration of methods for protecting artworks against style mimicry. Although generic diffusion models can easily mimic an artistic style, finetuning amplifies this capability, enabling the model to internalize and reproduce the style with higher fidelity and control. We hypothesize that certain cross-attention layers exhibit heightened sensitivity to artistic styles. Sensitivity is measured through activation strengths of attention layers in response to style and content representations, and assessing their correlations with features extracted from external models. Based on our findings, we introduce an efficient and lightweight protection strategy, StyleProtect, that achieves effective style defense against fine-tuned diffusion models by updating only selected cross-attention layers. Our experiments utilize a carefully curated artwork dataset based on WikiArt, comprising representative works from 30 artists known for their distinctive and influential styles and cartoon animations from the Anita dataset. The proposed method demonstrates promising performance in safeguarding unique styles of artworks and anime from malicious diffusion customization, while maintaining competitive imperceptibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13711 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models Tang, Qiuyu Krinsky, Joshua Bharati, Aparna Computer Vision and Pattern Recognition The rapid advancement of generative models, particularly diffusion-based approaches, has inadvertently facilitated their potential for misuse. Such models enable malicious exploiters to replicate artistic styles that capture an artist's creative labor, personal vision, and years of dedication in an inexpensive manner. This has led to a rise in the need and exploration of methods for protecting artworks against style mimicry. Although generic diffusion models can easily mimic an artistic style, finetuning amplifies this capability, enabling the model to internalize and reproduce the style with higher fidelity and control. We hypothesize that certain cross-attention layers exhibit heightened sensitivity to artistic styles. Sensitivity is measured through activation strengths of attention layers in response to style and content representations, and assessing their correlations with features extracted from external models. Based on our findings, we introduce an efficient and lightweight protection strategy, StyleProtect, that achieves effective style defense against fine-tuned diffusion models by updating only selected cross-attention layers. Our experiments utilize a carefully curated artwork dataset based on WikiArt, comprising representative works from 30 artists known for their distinctive and influential styles and cartoon animations from the Anita dataset. The proposed method demonstrates promising performance in safeguarding unique styles of artworks and anime from malicious diffusion customization, while maintaining competitive imperceptibility. |
| title | StyleProtect: Safeguarding Artistic Identity in Fine-tuned Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.13711 |