robusttorch's Introduction

DeepRobust

For more details about attacks and defenses, you can read this paper.

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

We would be glad if you find our work useful and cite the paper.

@article{xu2019adversarial,
  title={Adversarial attacks and defenses in images, graphs and text: A review},
  author={Xu, Han and Ma, Yao and Liu, Haochen and Deb, Debayan and Liu, Hui and Tang, Jiliang and Jain, Anil},
  journal={arXiv preprint arXiv:1909.08072},
  year={2019}
}

Requirements

python3
numpy
pytorch v1.2.0
matplotlib

Support Datasets

MNIST
CIFAR-10
ImageNet

Support Networks

SampleCNN
ResNet

Attack Methods

Attack Methods	Attack Type	Apply Domain	Links
LBFGS attack	White-Box	Image Classification	Intriguing Properties of Neural Networks
FGSM attack	White-Box	Image Classification	Explaining and Harnessing Adversarial Examples
PGD attack	White-Box	Image Classification	Towards Deep Learning Models Resistant to Adversarial Attacks
DeepFool attack	White-Box	Image Classification	DeepFool: a simple and accurate method to fool deep neural network
CW attack	White-Box	Image Classification	Towards Evaluating the Robustness of Neural Networks
Nattack	Black-Box	Image Classification	NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

Defense Methods

Defense Methods	Defense Type	Apply Domain	Links
FGSM training	Adverserial Training	Image Classification	Towards Deep Learning Models Resistant to Adversarial Attacks
PGD training	Adverserial Training	Image Classification	Intriguing Properties of Neural Networks
YOPO	Adverserial Training	Image Classification	You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
TRADES	Adverserial Training	Image Classification	Theoretically Principled Trade-off between Robustness and Accuracy

Recommend Projects