SuMa erases narrow concepts from text-to-image models by mapping the concept's token subspace onto a nearby reference subspace, achieving robustness against adversarial attacks with image quality close to standard erasure methods.
Muse: Text- to-image generation via masked generative transformers
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models
SuMa erases narrow concepts from text-to-image models by mapping the concept's token subspace onto a nearby reference subspace, achieving robustness against adversarial attacks with image quality close to standard erasure methods.