Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Last update: Dec 10, 2022

Related tags

Overview

AdvRush

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Environmental Set-up

Python == 3.6.12, PyTorch == 1.2.0, torchvision == 0.4.0

AdvRush Search Process

cd advrush && python train_search.py --batch_size 32 --gpu 0 --epochs 60 --a_gamma 0.01 --a_warmup_epochs 0 --w_warmup_epochs 60 --loss_hessian loss_cure

Adversarial Training

cd advrush && python adv_train.py --batch_size 64 --gpu 0 --epochs 200 --adv_loss pgd --arch ADVRUSH

Evaluation under PGD Attack

Prior to the evaluation process, add all necessary checkpoint files (preferably in the form of .pth.tar) to the /eval/checkpoints folder. To conduct white-box attacks,

cd eval &&
python pgd_attack.py --white-box-attack True --test-batch-size 10 --arch [arch_name] --checkpoint [./checkpoints/file_name.pth.tar] --data_type [cifar10/svhn]

To conduct black-box attacks,

cd eval &&
python pgd_attack.py --test-batch-size 10 --target_arch [target_arch] --target_checkpoint [./checkpoints/target_file.pth.tar] --source_arch [source_arch] --source_checkpoint [./checkpoints/source_file.pth.tar] --data_type cifar10

References

DARTS: Differentiable Architecture Search [ICLR '19] code paper

Robustness via Curvature Regularization, and Vice Versa [CVPR '19] code paper

Tradeoff-inspired Adversarial Defense via Surrogate-loss Minimization [ICML '19] code paper

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Related tags

Overview

AdvRush

Environmental Set-up

AdvRush Search Process

Adversarial Training

Evaluation under PGD Attack

References

Owner

Pytorch implementation of U-Net, R2U-Net, Attention U-Net, and Attention R2U-Net.

CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Implementation for "Domain-Specific Bias Filtering for Single Labeled Domain Generalization"

EgGateWayGetShell py脚本

Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labeling and Data Augmentation for Vision.

GNPy: Optical Route Planning and DWDM Network Optimization

Learning cell communication from spatial graphs of cells

Fortuitous Forgetting in Connectionist Networks

Paaster is a secure by default end-to-end encrypted pastebin built with the objective of simplicity.

LSTM-VAE Implementation and Relevant Evaluations

List of all dependencies affected by node-ipc malicious commit

ROCKET: Exceptionally fast and accurate time series classification using random convolutional kernels

Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs

VolumeGAN - 3D-aware Image Synthesis via Learning Structural and Textural Representations

Course about deep learning for computer vision and graphics co-developed by YSDA and Skoltech.

Keras-1D-ACGAN-Data-Augmentation

这是一个yolox-pytorch的源码，可以用于训练自己的模型。

AutoML library for deep learning

Some useful blender add-ons for SMPL skeleton's poses and global translation.