Robustness and Accuracy Could Be Reconcilable by (Proper) Definition

Code for the paper Robustness and Accuracy Could Be Reconcilable by (Proper) Definition (ICML 2022).

Environment settings and libraries we used in our experiments

This project is tested under the following environment settings:

• OS: Ubuntu 20.04.3
• GPU: NVIDIA A100
• Cuda: 11.1, Cudnn: v8.2
• Python: 3.9.5
• PyTorch: 1.8.0
• Torchvision: 0.9.0

Acknowledgement

The codes are modifed based on the PyTorch implementation of Rebuffi et al., 2021.

Requirements

• Install or download AutoAttack:

pip install git+https://github.com/fra31/auto-attack

• Download 1M DDPM generated data from the official implementation of Rebuffi et al., 2021:

Training Commands

To run the KL-based baselines (with 1M DDPM generated data), an example is:

python train-wa.py --data-dir 'cifar-data' \
    --log-dir 'trained_models' \
    --desc 'WRN28-10Swish_cifar10s_lr0p2_TRADES5_epoch400_bs512_fraction0p7_ls0p1' \
    --data cifar10s \
    --batch-size 512 \
    --model wrn-28-10-swish \
    --num-adv-epochs 400 \
    --lr 0.2 \
    --beta 5.0 \
    --unsup-fraction 0.7 \
    --aux-data-filename 'cifar10_ddpm.npz' \
    --ls 0.1

Here --ls 0.1 is inherent from the the code implementation of Rebuffi et al., 2021.

To run our methods (with 1M DDPM generated data), an example is:

python train-wa.py --data-dir 'cifar-data' \
    --log-dir 'trained_models' \
    --desc 'WRN28-10Swish_cifar10s_lr0p2_TRADES4_epoch400_bs512_fraction0p7_LSE' \
    --data cifar10s \
    --batch-size 512 \
    --model wrn-28-10-swish \
    --num-adv-epochs 400 \
    --lr 0.2 \
    --beta 4.0 \
    --unsup-fraction 0.7 \
    --aux-data-filename 'cifar10_ddpm.npz' \
    --LSE --ls 0

Here we only need to activate the flag --LSE and set --ls 0.

Pretrained checkpoints

Below are pretrained checkpoints of WRN-28-10 (Swish) and WRN-70-16 (Swish) with --beta=3.0:

• Downloading checkpoint to trained_models/mymodel/weights-best.pt
• Downloading argtxt to trained_models/mymodel/args.txt

Evaluation Commands

For evaluation under AutoAttack, run the command (taking our method as an example):

python eval-aa.py --data-dir 'cifar-data' \
    --log-dir 'trained_models' \
    --desc mymodel

Toy demos

To re-implement the toy demos, we could run:

python generate_toy_demo.py --demo PGDAT --divergence KL --divergence_C L1

The flag --demo refers to the objective used for training; --divergence refers to the used metric loss; --divergence_C refers to the metric calculating SCORE values. The Figures 1 and 2 in our paper are plotted by MATLAB using the script plot_toy_demo.m.

References

If you find the code useful for your research, please consider citing

@inproceedings{pang2022robustness,
  title={Robustness and Accuracy Could be Reconcilable by (Proper) Definition},
  author={Pang, Tianyu and Lin, Min and Yang, Xiao and Zhu, Jun and Yan, Shuicheng},
  booktitle={International Conference on Machine Learning (ICML)},
  year={2022}
}

and/or our related works

@inproceedings{wang2023better,
  title={Better Diffusion Models Further Improve Adversarial Training},
  author={Wang, Zekai and Pang, Tianyu and Du, Chao and Lin, Min and Liu, Weiwei and Yan, Shuicheng},
  booktitle={International Conference on Machine Learning (ICML)},
  year={2023}
}

@inproceedings{pang2021bag,
  title={Bag of Tricks for Adversarial Training},
  author={Pang, Tianyu and Yang, Xiao and Dong, Yinpeng and Su, Hang and Zhu, Jun},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2021}
}