AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917133220315136 |
|---|---|
| author | Wang, Yiming Chen, Jiahao Li, Qingming Zhang, Tong Zeng, Rui Yang, Xing Ji, Shouling |
| author_facet | Wang, Yiming Chen, Jiahao Li, Qingming Zhang, Tong Zeng, Rui Yang, Xing Ji, Shouling |
| contents | As text-to-image (T2I) models advance and gain widespread adoption, their associated safety concerns are becoming increasingly critical. Malicious users exploit these models to generate Not-Safe-for-Work (NSFW) images using harmful or adversarial prompts, underscoring the need for effective safeguards to ensure the integrity and compliance of model outputs. However, existing detection methods often exhibit low accuracy and inefficiency. In this paper, we propose AEIOU, a defense framework that is adaptable, efficient, interpretable, optimizable, and unified against NSFW prompts in T2I models. AEIOU extracts NSFW features from the hidden states of the model's text encoder, utilizing the separable nature of these features to detect NSFW prompts. The detection process is efficient, requiring minimal inference time. AEIOU also offers real-time interpretation of results and supports optimization through data augmentation techniques. The framework is versatile, accommodating various T2I architectures. Our extensive experiments show that AEIOU significantly outperforms both commercial and open-source moderation tools, achieving over 95\% accuracy across all datasets and improving efficiency by at least tenfold. It effectively counters adaptive attacks and excels in few-shot and multi-label scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18123 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models Wang, Yiming Chen, Jiahao Li, Qingming Zhang, Tong Zeng, Rui Yang, Xing Ji, Shouling Cryptography and Security Computation and Language As text-to-image (T2I) models advance and gain widespread adoption, their associated safety concerns are becoming increasingly critical. Malicious users exploit these models to generate Not-Safe-for-Work (NSFW) images using harmful or adversarial prompts, underscoring the need for effective safeguards to ensure the integrity and compliance of model outputs. However, existing detection methods often exhibit low accuracy and inefficiency. In this paper, we propose AEIOU, a defense framework that is adaptable, efficient, interpretable, optimizable, and unified against NSFW prompts in T2I models. AEIOU extracts NSFW features from the hidden states of the model's text encoder, utilizing the separable nature of these features to detect NSFW prompts. The detection process is efficient, requiring minimal inference time. AEIOU also offers real-time interpretation of results and supports optimization through data augmentation techniques. The framework is versatile, accommodating various T2I architectures. Our extensive experiments show that AEIOU significantly outperforms both commercial and open-source moderation tools, achieving over 95\% accuracy across all datasets and improving efficiency by at least tenfold. It effectively counters adaptive attacks and excels in few-shot and multi-label scenarios. |
| title | AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models |
| topic | Cryptography and Security Computation and Language |
| url | https://arxiv.org/abs/2412.18123 |