Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective

arXiv:2402.18607v1 Announce Type: cross
Abstract: Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distribution coverage. Accordingly, proposals are made for sharing pre-trained diffusion models across different organizations, as a way of improving data utilization while enhancing privacy protection by avoiding sharing private data directly. However, the potential risks associated with such an approach have not been comprehensively examined.
In this paper, we take …

academia adversarial arxiv attention cs.ai cs.cr cs.lg diffusion models distribution fairness generative industry organizations performance perspective privacy proposals quality risks sharing terms