To normalize or not to normalize?

Documentation | Paper | Samples

[AAAI 2021] DeepRobust is a PyTorch adversarial library for attack and defense methods on images and graphs.

If you are new to DeepRobust, we highly suggest you read the documentation page or the following content in this README to learn how to use it.
If you have any questions or suggestions regarding this library, feel free to create an issue here. We will reply as soon as possible :)

List of including algorithms can be found in [Image Package] and [Graph Package].

Environment & Installation

Usage

Image Attack and Defense
Graph Attack and Defense

Acknowledgement

For more details about attacks and defenses, you can read the following papers.

If our work could help your research, please cite: DeepRobust: A PyTorch Library for Adversarial Attacks and Defenses

@article{li2020deeprobust,
  title={Deeprobust: A pytorch library for adversarial attacks and defenses},
  author={Li, Yaxin and Jin, Wei and Xu, Han and Tang, Jiliang},
  journal={arXiv preprint arXiv:2005.06149},
  year={2020}
}

Changelog

[11/2023] Try git clone https://github.com/DSE-MSU/DeepRobust.git; cd DeepRobust; python setup_empty.py install to directly install DeepRobust without installing dependency packages.
[11/2023] DeepRobust 0.2.9 Released. Please try pip install deeprobust==0.2.9. We have fixed the OOM issue of metattack on new pytorch versions.
[06/2023] We have added a backdoor attack UGBA, WWW'23 to graph package. We can now use UGBA to conduct unnoticeable backdoor attack on large-scale graphs such as ogb-arxiv (see example in test_ugba.py)!
[02/2023] DeepRobust 0.2.8 Released. Please try pip install deeprobust==0.2.8! We have added a scalable attack PRBCD, NeurIPS'21 to graph package. We can now use PRBCD to attack large-scale graphs such as ogb-arxiv (see example in test_prbcd.py)!
[02/2023] Add a robust model AirGNN, NeurIPS'21 to graph package. Try python examples/graph/test_airgnn.py! See details in test_airgnn.py
[11/2022] DeepRobust 0.2.6 Released. Please try pip install deeprobust==0.2.6! We have more updates coming. Please stay tuned!
[11/2021] A subpackage that includes popular black box attacks in image domain is released. Find it here. Link
[11/2021] DeepRobust 0.2.4 Released. Please try pip install deeprobust==0.2.4!
[10/2021] add scalable attack and MedianGCN. Thank Jintang for his contribution!
[06/2021] [Image Package] Add preprocessing method: APE-GAN.
[05/2021] DeepRobust is published at AAAI 2021. Check here!
[05/2021] DeepRobust 0.2.2 Released. Please try pip install deeprobust==0.2.2!
[04/2021] [Image Package] Add support for ImageNet. See details in test_ImageNet.py
[04/2021] [Graph Package] Add support for OGB datasets. See more details in the tutorial page.
[03/2021] [Graph Package] Added node embedding attack and victim models! See this tutorial page.
[02/2021] [Graph Package] DeepRobust now provides tools for converting the datasets between Pytorch Geometric and DeepRobust. See more details in the tutorial page! DeepRobust now also support GAT, Chebnet and SGC based on pyg; see details in test_gat.py, test_chebnet.py and test_sgc.py
[12/2020] DeepRobust now can be installed via pip! Try pip install deeprobust!
[12/2020] [Graph Package] Add four more datasets and one defense algorithm. More details can be found here. More datasets and algorithms will be added later. Stay tuned :)
[07/2020] Add documentation page!
[06/2020] Add docstring to both image and graph package

Basic Environment

python >= 3.6 (python 3.5 should also work)
pytorch >= 1.2.0

see setup.py or requirements.txt for more information.

Installation

Install from pip

pip install deeprobust

Install from source

git clone https://github.com/DSE-MSU/DeepRobust.git
cd DeepRobust
python setup.py install

If you find the dependencies are hard to install, please try the following: python setup_empty.py install (only install deeprobust without installing other packages)

Test Examples

python examples/image/test_PGD.py
python examples/image/test_pgdtraining.py
python examples/graph/test_gcn_jaccard.py --dataset cora
python examples/graph/test_mettack.py --dataset cora --ptb_rate 0.05

Usage

Image Attack and Defense

Train model

Example: Train a simple CNN model on MNIST dataset for 20 epoch on gpu.
```
import deeprobust.image.netmodels.train_model as trainmodel
trainmodel.train('CNN', 'MNIST', 'cuda', 20)
```
Model would be saved in deeprobust/trained_models/.

Instantiated attack methods and defense methods.

Example: Generate adversary example with PGD attack.

from deeprobust.image.attack.pgd import PGD
from deeprobust.image.config import attack_params
from deeprobust.image.utils import download_model
import torch
import deeprobust.image.netmodels.resnet as resnet
from torchvision import transforms,datasets

URL = "https://github.com/I-am-Bot/deeprobust_model/raw/master/CIFAR10_ResNet18_epoch_20.pt"
download_model(URL, "$MODEL_PATH$")

model = resnet.ResNet18().to('cuda')
model.load_state_dict(torch.load("$MODEL_PATH$"))
model.eval()

transform_val = transforms.Compose([transforms.ToTensor()])
test_loader  = torch.utils.data.DataLoader(
                datasets.CIFAR10('deeprobust/image/data', train = False, download=True,
                transform = transform_val),
                batch_size = 10, shuffle=True)

x, y = next(iter(test_loader))
x = x.to('cuda').float()

adversary = PGD(model, 'cuda')
Adv_img = adversary.generate(x, y, **attack_params['PGD_CIFAR10'])

Example: Train defense model.

from deeprobust.image.defense.pgdtraining import PGDtraining
from deeprobust.image.config import defense_params
from deeprobust.image.netmodels.CNN import Net
import torch
from torchvision import datasets, transforms 

model = Net()
train_loader = torch.utils.data.DataLoader(
                datasets.MNIST('deeprobust/image/defense/data', train=True, download=True,
                                transform=transforms.Compose([transforms.ToTensor()])),
                                batch_size=100,shuffle=True)

test_loader = torch.utils.data.DataLoader(
              datasets.MNIST('deeprobust/image/defense/data', train=False,
                            transform=transforms.Compose([transforms.ToTensor()])),
                            batch_size=1000,shuffle=True)

defense = PGDtraining(model, 'cuda')
defense.generate(train_loader, test_loader, **defense_params["PGDtraining_MNIST"])

More example code can be found in deeprobust/examples.

Use our evulation program to test attack algorithm against defense.

Example:

cd DeepRobust
python examples/image/test_train.py
python deeprobust/image/evaluation_attack.py

Graph Attack and Defense

Attacking Graph Neural Networks

Load dataset

import torch
import numpy as np
from deeprobust.graph.data import Dataset
from deeprobust.graph.defense import GCN
from deeprobust.graph.global_attack import Metattack

data = Dataset(root='/tmp/', name='cora', setting='nettack')
adj, features, labels = data.adj, data.features, data.labels
idx_train, idx_val, idx_test = data.idx_train, data.idx_val, data.idx_test
idx_unlabeled = np.union1d(idx_val, idx_test)

Set up surrogate model

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
surrogate = GCN(nfeat=features.shape[1], nclass=labels.max().item()+1, nhid=16,
                with_relu=False, device=device)
surrogate = surrogate.to(device)
surrogate.fit(features, adj, labels, idx_train)

Set up attack model and generate perturbations

model = Metattack(model=surrogate, nnodes=adj.shape[0], feature_shape=features.shape, device=device)
model = model.to(device)
perturbations = int(0.05 * (adj.sum() // 2))
model.attack(features, adj, labels, idx_train, idx_unlabeled, perturbations, ll_constraint=False)
modified_adj = model.modified_adj

For more details please refer to mettack.py or run python examples/graph/test_mettack.py --dataset cora --ptb_rate 0.05

Defending Against Graph Attacks

Load dataset

import torch
from deeprobust.graph.data import Dataset, PtbDataset
from deeprobust.graph.defense import GCN, GCNJaccard
import numpy as np
np.random.seed(15)

# load clean graph
data = Dataset(root='/tmp/', name='cora', setting='nettack')
adj, features, labels = data.adj, data.features, data.labels
idx_train, idx_val, idx_test = data.idx_train, data.idx_val, data.idx_test

# load pre-attacked graph by mettack
perturbed_data = PtbDataset(root='/tmp/', name='cora')
perturbed_adj = perturbed_data.adj

Test

# Set up defense model and test performance
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = GCNJaccard(nfeat=features.shape[1], nclass=labels.max()+1, nhid=16, device=device)
model = model.to(device)
model.fit(features, perturbed_adj, labels, idx_train)
model.eval()
output = model.test(idx_test)

# Test on GCN
model = GCN(nfeat=features.shape[1], nclass=labels.max()+1, nhid=16, device=device)
model = model.to(device)
model.fit(features, perturbed_adj, labels, idx_train)
model.eval()
output = model.test(idx_test)

For more details please refer to test_gcn_jaccard.py or run python examples/graph/test_gcn_jaccard.py --dataset cora

Sample Results

adversary examples generated by fgsm:

Left:original, classified as 6; Right:adversary, classified as 4.

Serveral trained models can be found here: https://drive.google.com/open?id=1uGLiuCyd8zCAQ8tPz9DDUQH6zm-C4tEL

Acknowledgement

Some of the algorithms are referred to paper authors' implementations. References can be found at the top of each file.

Implementation of network structure are referred to weiaicunzai's github. Original code can be found here: pytorch-cifar100

Thanks to their outstanding works!

	self.adj = self.load_data()
	self.target_nodes = None

	def load_data(self):
	if not osp.exists(self.data_filename):
	self.download_npz()
	print('Loading {} dataset perturbed by {} {}...'.format(self.name, self.ptb_rate, self.attack_method))

	if self.attack_method == 'meta':
	warnings.warn("the pre-attacked graph is perturbed, using the data splits under seed 15 (default seed), so if you are going to verify the attacking performance, you should use the same data splits.")
	adj = sp.load_npz(self.data_filename)

	if self.attack_method == 'nettack':
	# assert True, "Will update pre-attacked data by nettack soon"
	warnings.warn("the pre-attacked graph is perturbed, using the data splits under seed 15 (default seed), so if you are going to verify the attacking performance, you should use the same seed (15).")
	adj = sp.load_npz(self.data_filename)
	self.target_nodes = self.get_target_nodes()
	return adj

	for j in range(self.train_iters):
	hidden = features
	for ix, w in enumerate(self.weights):
	b = self.biases[ix] if self.with_bias else 0
	if self.sparse_features:
	hidden = adj_norm @ torch.spmm(hidden, w) + b
	else:
	hidden = adj_norm @ hidden @ w + b
	if self.with_relu:
	hidden = F.relu(hidden)

	output = F.log_softmax(hidden, dim=1)

	hidden = features
	for ix, w in enumerate(self.weights):
	b = self.biases[ix] if self.with_bias else 0
	if self.sparse_features:
	hidden = adj_norm @ torch.spmm(hidden, w) + b
	else:
	hidden = adj_norm @ hidden @ w + b
	if self.with_relu:
	hidden = F.relu(hidden)

	output = F.log_softmax(hidden, dim=1)

	def _cosine_similarity(self, a, b):
	inner_product = (features[n1] * features[n2]).sum()
	C = inner_product / np.sqrt(np.square(a).sum() + np.square(b).sum())

dse-msu / deeprobust Goto Github PK

deeprobust's Introduction

Changelog

Basic Environment

Installation

Install from pip

Install from source

Test Examples

Usage

Image Attack and Defense

Graph Attack and Defense

Attacking Graph Neural Networks

Defending Against Graph Attacks

Sample Results

Acknowledgement

deeprobust's People

Contributors

Stargazers

Watchers

Forkers

deeprobust's Issues

Recommend Projects

Recommend Topics

Recommend Org