Skip to yearly menu bar Skip to main content


Poster
in
Workshop: New Frontiers in Learning, Control, and Dynamical Systems

Tendiffpure: Tensorizing Diffusion Models for Purification

Zhou Derun · Mingyuan Bai · Qibin Zhao


Abstract: Diffusion models are effective purification methods where the noises or adversarial attacks are removed using generative approaches before pre-existing classifiers conducting classification tasks. However, the efficiency of diffusion models is still a concern and existing solutions are based on knowledge distillation which can jeopardize the generation quality because of the small number of generation steps. Hence we propose Tendiffpure as a tensorized diffusion models to compress diffusion models for purification. Unlike the knowledge distillation methods, we directly compress u-nets as backbones of diffusion models using tensor-train decomposition which reduce the number of parameters and captures more spatial information in multi-dimensional data such as images. The space complexity is reduced from O(N2) to O(NR2) with R4. Experimental results show that Tendiffpure can more efficiently generate high quality purified results and outperform the baselines purification methods on CIFAR-10, FashionMNIST and MNIST datasets for two noises and one adversarial attack.

Chat is not available.