Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
张天缘 d030f0d698 | 1 year ago | |
---|---|---|
Test4_googlenet | 1 year ago | |
Test5_resnet | 1 year ago | |
Test11_efficientnetV2 | 1 year ago | |
data | 1 year ago | |
data_aug_test | 1 year ago | |
frost | 1 year ago | |
model | 1 year ago | |
saved_models | 1 year ago | |
.gitignore | 1 year ago | |
README.md | 1 year ago | |
adv_gen.py | 1 year ago | |
class_indices.json | 1 year ago | |
data.py | 1 year ago | |
data_aug.py | 1 year ago | |
data_transform.py | 1 year ago | |
eval.py | 1 year ago | |
inference.py | 1 year ago | |
train.py | 1 year ago | |
utils.py | 1 year ago |
Paper |
Checkpoints |
Homepage
Official PyTorch Implementation
Sen Pei, Jiaxi Sun, Xin Zhang, Qing Li
Institute of Automation, Chinese Academy of Sciences
pytorch
, no strict version constraint.GradientConcealment()
in model/robust_layer.py
as the top layer of your model in forward()
.Model | Method | Top 1 Acc | FGSM Linf=8/255 | PGD L1=1600 | PGD L2=8.0 | PGD Linf=8/255 | C&W L2=8.0 |
---|---|---|---|---|---|---|---|
ResNet-50 | Vanilla | 77.89 | 31.77 | 0.01 | 0.01 | 0.00 | 0.21 |
ResNet-50 | GCM | 78.57 | 95.18 | 94.82 | 94.41 | 97.38 | 95.11 |
WideResNet-50 | Vanilla | 78.21 | 20.88 | 0.36 | 0.61 | 0.50 | 0.21 |
WideResNet-50 | GCM | 78.08 | 96.06 | 94.46 | 94.51 | 97.69 | 95.66 |
DenseNet-121 | Vanilla | 74.86 | 16.82 | 0.04 | 0.05 | 0.06 | 0.12 |
DenseNet-121 | GCM | 74.71 | 94.98 | 94.31 | 94.08 | 97.16 | 95.49 |
EfficientNet-B4 | Vanilla | 71.52 | 1.23 | 0.36 | 0.28 | 0.20 | 1.88 |
EfficientNet-B4 | GCM | 71.76 | 94.68 | 89.95 | 90.87 | 97.97 | 93.07 |
ViT-B/16 | Vanilla | 79.46 | 15.86 | 0.00 | 0.00 | 0.00 | 0.90 |
ViT-B/16 | GCM | 79.47 | 92.24 | 94.94 | 95.07 | 98.24 | 93.31 |
Swin-Transformer-S | Vanilla | 82.93 | 16.93 | 0.20 | 0.00 | 0.00 | 0.76 |
Swin-Transformer-S | GCM | 82.79 | 94.38 | 90.71 | 91.04 | 98.77 | 92.31 |
data_aug.py supports the following operations currently:
transforms.Resize(256)
transforms.RandomResizedCrop(224)
Data augmentation schemes
ResizedPaddingLayer
.ResizedPaddingLayer
.python -m torch.distributed.launch --nproc_per_node=5 train.py --batch_size 64 --n_gpus=5
nproc_per_node
and n_gpus
to utilize them.@article{Pei2022Grad,
title={Gradient Concealment: Free Lunch for Defending Adversarial Attacks},
author={Sen Pei, Jiaxi Sun, Xiaopeng Zhang and Gaofeng Meng},
archivePrefix={arXiv},
primaryClass={cs.CV},
year={2022}
}
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》