Do not think about pink elephant!
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_ | 1866912096674906112 |
|---|---|
| author | Hwang, Kyomin Kim, Suyoung Lee, JunHoo Kwak, Nojun |
| author_facet | Hwang, Kyomin Kim, Suyoung Lee, JunHoo Kwak, Nojun |
| contents | Large Models (LMs) have heightened expectations for the potential of general AI as they are akin to human intelligence. This paper shows that recent large models such as Stable Diffusion and DALL-E3 also share the vulnerability of human intelligence, namely the "white bear phenomenon". We investigate the causes of the white bear phenomenon by analyzing their representation space. Based on this analysis, we propose a simple prompt-based attack method, which generates figures prohibited by the LM provider's policy. To counter these attacks, we introduce prompt-based defense strategies inspired by cognitive therapy techniques, successfully mitigating attacks by up to 48.22\%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15154 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Do not think about pink elephant! Hwang, Kyomin Kim, Suyoung Lee, JunHoo Kwak, Nojun Computation and Language Artificial Intelligence Large Models (LMs) have heightened expectations for the potential of general AI as they are akin to human intelligence. This paper shows that recent large models such as Stable Diffusion and DALL-E3 also share the vulnerability of human intelligence, namely the "white bear phenomenon". We investigate the causes of the white bear phenomenon by analyzing their representation space. Based on this analysis, we propose a simple prompt-based attack method, which generates figures prohibited by the LM provider's policy. To counter these attacks, we introduce prompt-based defense strategies inspired by cognitive therapy techniques, successfully mitigating attacks by up to 48.22\%. |
| title | Do not think about pink elephant! |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2404.15154 |