Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks

Abstract

Diffusion models have achieved remarkable success in generative tasks across various areas, however their training process raises significant privacy concerns, particularly under membership inference attacks (MIAs). Prior studies on privacy-preserving of diffusion models fail to balance privacy, utility, and efficiency. To address this gap, we propose a novel framework of privacy-preserving diffusion models, Adaptive Diffusion Freezing (ADF), which can defend against MIAs with better trade-off.

Categories

Framework mappings

Suggested from the entry's categories.

@misc{guo2026adaptive,
  title = {{Adaptive Diffusion Freezing: Privacy-preserving Diffusion Models Against Membership Inference Attacks}},
  author = {Jialu Guo and Xiao Han and Junjie Wu},
  year = {2026},
  month = sep,
  eprint = {2609.10608},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.10608}
}