Hateful optical illusions generated with Stable Diffusion and ControlNet evade current moderation classifiers (best accuracy 0.245) and vision-language models (best accuracy 0.102), with simple image transformations substantially improving detection.
https://openai.com/index/hello-gpt-4o
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Hateful optical illusions generated with Stable Diffusion and ControlNet evade current moderation classifiers (best accuracy 0.245) and vision-language models (best accuracy 0.102), with simple image transformations substantially improving detection.