PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining

Kecen Li, Institute of Automation, Chinese Academy of Sciences; Chen Gong, University of Virginia; Zhixiang Li, University of Bristol; Yuzhong Zhao, University of Chinese Academy of Science; Xinwen Hou, Institute of Automation, Chinese Academy of Sciences; Tianhao Wang, University of Virginia