Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing Peiran Dong 1 Bingjie Wang 1 Song Guo 2 Junxiao Wang

Recent advancements in vision-language-to-image (VL2I) diffusion generation have made significant progress. While generating images from broad visionlanguage inputs holds promise, it also raises concerns about potential misuse, such as copying artistic styles without permission, which could have legal and social consequences.