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

Last update: Dec 10, 2022

Related tags

Deep Learning advrush

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

Comments

Reproduce the result

Hi ! Thanks for sharing the code. I am unable to reproduce the result from the paper. Using the command provided, I trained ADVRUSH (adv training) and got 85.69% clean ACC and 45.45% PGD20 while the paper reported 87.3% clean ACC and 53.07% PGD20. What am I missing here?

opened by tamltlkdn 2

Adversarial-Information-Bottleneck - Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck (NeurIPS21)

NeurIPS 2021 Title: Distilling Robust and Non-Robust Features in Adversarial Exa

35 Dec 26, 2022

Code image classification of MNIST dataset using different architectures: simple linear NN, autoencoder, and highway network

Deep Learning for image classification pip install -r http://webia.lip6.fr/~baskiotisn/requirements-amal.txt Train an autoencoder python3 train_auto

0 Mar 30, 2022

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021) authors: Boris Knyazev, Michal Drozdzal, Graham Taylor, Adriana Romero-Soriano Overv

462 Jan 3, 2023

Code for "Searching for Efficient Multi-Stage Vision Transformers"

Searching for Efficient Multi-Stage Vision Transformers This repository contains the official Pytorch implementation of "Searching for Efficient Multi

62 Oct 25, 2022

The code for our paper "AutoSF: Searching Scoring Functions for Knowledge Graph Embedding"

AutoSF The code for our paper "AutoSF: Searching Scoring Functions for Knowledge Graph Embedding" and this paper has been accepted by ICDE2020. News:

64 Dec 17, 2022

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

235 Dec 26, 2022

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021] Release Notes The offical PyTorch implementation of NeMo, p

76 Nov 23, 2022

The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

Watermark-Robustness-Toolbox - Official PyTorch Implementation This repository contains the official PyTorch implementation of the following paper to

49 Dec 19, 2022

An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

MixHop and N-GCN ⠀ A PyTorch implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019)

393 Dec 13, 2022

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

You might also like...

Adversarial-Information-Bottleneck - Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck (NeurIPS21)

Code image classification of MNIST dataset using different architectures: simple linear NN, autoencoder, and highway network

Code for Parameter Prediction for Unseen Deep Architectures (NeurIPS 2021)

Code for "Searching for Efficient Multi-Stage Vision Transformers"

The code for our paper "AutoSF: Searching Scoring Functions for Knowledge Graph Embedding"

Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

The official implementation of NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [ICLR-2021]. https://arxiv.org/pdf/2101.12378.pdf

The official implementation of the IEEE S&P`22 paper "SoK: How Robust is Deep Neural Network Image Classification Watermarking".

An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

Comments

Reproduce the result

Owner

Code for the paper: Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization (https://arxiv.org/abs/2002.11798)

Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.

Code for the paper "Adversarially Regularized Autoencoders (ICML 2018)" by Zhao, Kim, Zhang, Rush and LeCun

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation (CVPR 2021)

Official PyTorch implementation of N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras (ICCV 2021)

Official repository of OFA. Paper: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Open source implementation of AceNAS: Learning to Rank Ace Neural Architectures with Weak Supervision of Weight Sharing

An experimental technique for efficiently exploring neural architectures.

Learning Versatile Neural Architectures by Propagating Network Codes

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"