most citedTowards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models

5 citations · 11 across the 6 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2024

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models

Sanghyun Kim, Moonseok Choi, Jinwoo Shin +1

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: sa…