When Image Generation Goes Wrong: A Safety Analysis of Stable Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914009970638848 |
|---|---|
| author | Schneider, Matthias Hagendorff, Thilo |
| author_facet | Schneider, Matthias Hagendorff, Thilo |
| contents | Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW, violent, and personally sensitive material. We demonstrate that these models respond to harmful prompts by generating inappropriate content, which frequently displays troubling biases, such as the disproportionate portrayal of Black individuals in violent contexts. Our findings demonstrate a complete lack of any refusal behavior or safety measures in the models observed. We emphasize the importance of addressing this issue as image generation technologies continue to become more accessible and incorporated into everyday applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15516 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | When Image Generation Goes Wrong: A Safety Analysis of Stable Diffusion Models Schneider, Matthias Hagendorff, Thilo Computers and Society Text-to-image models are increasingly popular and impactful, yet concerns regarding their safety and fairness remain. This study investigates the ability of ten popular Stable Diffusion models to generate harmful images, including NSFW, violent, and personally sensitive material. We demonstrate that these models respond to harmful prompts by generating inappropriate content, which frequently displays troubling biases, such as the disproportionate portrayal of Black individuals in violent contexts. Our findings demonstrate a complete lack of any refusal behavior or safety measures in the models observed. We emphasize the importance of addressing this issue as image generation technologies continue to become more accessible and incorporated into everyday applications. |
| title | When Image Generation Goes Wrong: A Safety Analysis of Stable Diffusion Models |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2411.15516 |