IMMA: Immunizing text-to-image Models against Malicious Adaptation
CoRR(2023)
摘要
Advancements in text-to-image models and fine-tuning methods have led to the
increasing risk of malicious adaptation, i.e., fine-tuning to generate harmful
unauthorized content. Recent works, e.g., Glaze or MIST, have developed
data-poisoning techniques which protect the data against adaptation methods. In
this work, we consider an alternative paradigm for protection. We propose to
“immunize” the model by learning model parameters that are difficult for the
adaptation methods when fine-tuning malicious content; in short IMMA. Empirical
results show IMMA's effectiveness against malicious adaptations, including
mimicking the artistic style and learning of inappropriate/unauthorized
content, over three adaptation methods: LoRA, Textual-Inversion, and
DreamBooth.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要