Summarizing LLM-obfuscated text-to-image prompts before classification improves content-moderation F1 scores on the new ATTIP dataset.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
Summarizing LLM-obfuscated text-to-image prompts before classification improves content-moderation F1 scores on the new ATTIP dataset.