Abstract
We discover that DALLE-2 seems to have a hidden vocabulary that can be used to generate images with absurd prompts. For example, it seems that Apoploe vesrreaitais means birds and Contarra ccetnxniams luryca tanniounons (sometimes) means bugs or pests. We find that these prompts are often consistent in isolation but also sometimes in combinations. We present our black-box method to discover words that seem random but have some correspondence to visual concepts. This creates important security and interpretability challenges.
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2206.00169 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2206.00169 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2206.00169 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a
collection
to link it from this page.