GRACE: Adaptive Concept Erasure with Geometry-Guided Retention in Diffusion Models

Qinghui Gong, Yihuai Liang, Yuanlun Xie +3

Text-to-image (T2I) diffusion models inevitably internalize sensitive or non-compliant concepts from large-scale pretraining data, necessitating post-hoc concept erasure. However,…