Roy Ganz • Bahjat Kawar • Michael Elad

[ICML 2023 - Oral] Official Code Repository of Do Perceptually Aligned Gradients Imply Robustness?

First, clone this repository:

git clone https://github.com/royg27/PAG-ROB.git
cd PAG-ROB

Next, to install the requirements in a new conda environment, run:

conda env create -f environment.yml

The Perceptually Aligned Gradients' realization for the Score-Based Gradients for the CIFAR-10 dataset is provided in the following table:

The data should be placed in the data folder, forming the following structure:

PAG-ROB
├── configs
│   ├── ......
├── data
│   ├── c10_sbg_data.pt
│   ├── c10_sbg_label.pt
├── models
│   ├── ......
├── TRAIN_CIFAR10.py

python TRAIN_CIFAR10.py --config_path <config>

where <config> specifies the desired training configuration (e.g., configs/cifar10_sbg_rn18.yaml)

We provide pretrained checkpoints on the CIFAR-10 dataset in the table below:

If you find this code or data to be useful for your research, please consider citing it.

@misc{ganz2023perceptually,
      title={Do Perceptually Aligned Gradients Imply Adversarial Robustness?}, 
      author={Roy Ganz and Bahjat Kawar and Michael Elad},
      year={2023},
      eprint={2207.11378},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}