暂无评分数据
ICLR 2024
MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Synthesis Via Meta-learning
TL;DR
We propose MetaCloak, a robust solution utilizing meta-learning and transformation-robust noise crafting to prevent unauthorized, subject-driven text-to-image synthesis by DreamBooth models.
摘要
关键词
Poisoning AttackUnauthorized SynthesisDreamBoothText-to-Image Diffusion Models
评审与讨论
暂无评审记录