SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910653406511104 |
|---|---|
| author | Li, Xinfeng Yang, Yuchen Deng, Jiangyi Yan, Chen Chen, Yanjiao Ji, Xiaoyu Xu, Wenyuan |
| author_facet | Li, Xinfeng Yang, Yuchen Deng, Jiangyi Yan, Chen Chen, Yanjiao Ji, Xiaoyu Xu, Wenyuan |
| contents | Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts -- inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance. Furthermore, our constructed benchmark of adversarial prompts provides a basis for future development and evaluation of anti-NSFW-generation methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06666 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models Li, Xinfeng Yang, Yuchen Deng, Jiangyi Yan, Chen Chen, Yanjiao Ji, Xiaoyu Xu, Wenyuan Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Cryptography and Security Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating not-safe-for-work (NSFW) content, particularly in sexually explicit scenarios. Existing countermeasures mostly focus on filtering inappropriate inputs and outputs, or suppressing improper text embeddings, which can block sexually explicit content (e.g., naked) but may still be vulnerable to adversarial prompts -- inputs that appear innocent but are ill-intended. In this paper, we present SafeGen, a framework to mitigate sexual content generation by text-to-image models in a text-agnostic manner. The key idea is to eliminate explicit visual representations from the model regardless of the text input. In this way, the text-to-image model is resistant to adversarial prompts since such unsafe visual representations are obstructed from within. Extensive experiments conducted on four datasets and large-scale user studies demonstrate SafeGen's effectiveness in mitigating sexually explicit content generation while preserving the high-fidelity of benign images. SafeGen outperforms eight state-of-the-art baseline methods and achieves 99.4% sexual content removal performance. Furthermore, our constructed benchmark of adversarial prompts provides a basis for future development and evaluation of anti-NSFW-generation methods. |
| title | SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2404.06666 |