2024
IMMA: Immunizing text-to-image Models against Malicious Adaptation
ECCV 2024poster
"Advancements in open-sourced text-to-image models and fine-tuning methods have led to the increasing risk of malicious adaptation, , fine-tuning to generate harmful/unauthorized content. Recent works, , Glaze or MIST, have developed data-poisoning techniques which protect the data against adaptatio…