Diffusion Models for Adversarial Purification

Authors: Weili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, Animashree Anandkumar

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on three image datasets including CIFAR10, Image Net and Celeb A-HQ with three classifier architectures including Res Net, Wide Res Net and Vi T demonstrate that our method achieves the state-of-the-art results, outperforming current adversarial training and adversarial purification methods, often by a large margin.
Researcher Affiliation Collaboration 1NVIDIA 2Caltech 3ASU.
Pseudocode No The paper describes mathematical equations and processes but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No Project page: https://diffpure.github.io.
Open Datasets Yes We consider three datasets for evaluation: CIFAR-10 (Krizhevsky, 2009), Celeb A-HQ (Karras et al., 2018), and Image Net (Deng et al., 2009).
Dataset Splits Yes Particularly, we compare with the state-of-the-art defense methods reported by the standardized benchmark Robust Bench (Croce et al., 2020) on CIFAR-10 and Image Net while comparing with other adversarial purification methods on CIFAR-10 and Celeb A-HQ following their settings.
Hardware Specification Yes Table 14. Inference time with Diff Pure (t > 0) and without Diff Pure (t = 0) for a single image on an NVIDIA V100 GPU
Software Dependencies No In experiments, we use the adjoint framework for SDEs named adjoint sdeint in the Torch SDE library: https://github.com/google-research/ torchsde for both adversarial purification and gradient evaluation.
Experiment Setup Yes In our method, the diffusion timestep is t = 0.1. (from Table 1 caption)