Diffusion models improve adversarial robustness mainly by compressing the input space, while the large gains reported earlier mostly come from evaluation randomness.
advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
advertorch is a toolbox for adversarial robustness research. It contains various implementations for attacks, defenses and robust training methods. advertorch is built on PyTorch (Paszke et al., 2017), and leverages the advantages of the dynamic computational graph to provide concise and efficient reference implementations. The code is licensed under the LGPL license and is open sourced at https://github.com/BorealisAI/advertorch .
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How Do Diffusion Models Improve Adversarial Robustness?
Diffusion models improve adversarial robustness mainly by compressing the input space, while the large gains reported earlier mostly come from evaluation randomness.