Typography inserted into input images can manipulate CLIP-guided image generation models to produce harmful or biased content, and existing text-focused defenses do not catch it.
Un- veiling typographic deceptions: Insights of the typographic vulnerability in large vision-language model.European Con- ference on Computer Vision (ECCV), 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models
Typography inserted into input images can manipulate CLIP-guided image generation models to produce harmful or biased content, and existing text-focused defenses do not catch it.