REDEditing injects harmful concepts into text-to-image models by editing cross-attention weights with relationship-matched attribute pairs, achieving 91.3% attack success while keeping benign outputs close to the original model.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
REDEditing injects harmful concepts into text-to-image models by editing cross-attention weights with relationship-matched attribute pairs, achieving 91.3% attack success while keeping benign outputs close to the original model.