Defending graph neural networks against adversarial attacks (NeurIPS 2020)

Overview

GNNGuard: Defending Graph Neural Networks against Adversarial Attacks

Authors: Xiang Zhang ([email protected]), Marinka Zitnik ([email protected])

Project website

Overview

This repository contains python codes and datasets necessary to run the GNNGuard algorithm. GNNGuard is a general defense approach against a variety of poisoning adversarial attacks that perturb the discrete graph structure. GNNGuard can be straightforwardly incorporated into any GNN models to prevent the misclassification caused by poisoning adversarial attacks on graphs. Please see our paper for more details on the algorithm.

Key Idea of GNNGuard

Deep learning methods for graphs achieve remarkable performance on many tasks. However, despite the proliferation of such methods and their success, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs). By integrating with the proposed GNNGuard, the GNN classifier can correctly classify the target node even under strong adversarial attacks.

The key idea of GNNGuard is to detect and quantify the relationship between the graph structure and node features, if one exists, and then exploit that relationship to mitigate negative effects of the attack. GNNGuard learns how to best assign higher weights to edges connecting similar nodes while pruning edges between unrelated nodes. In specific, instead of the neural message passing of typical GNN (shown as A), GNNGuard (B) controls the message stream such as blocking the message from irrelevent neighbors but strengthening messages from highly-related ones. Importantly, we are the first model that can defend heterophily graphs (\eg, with structural equivalence) while all the existing defenders only considering homophily graphs.

Running the code

The GNNGuard is evluated under three typical adversarial attacks including Direct Targeted Attack (Nettack-Di), Influence Targeted Attack (Nettack-In), and Non-Targeted Attack (Mettack). In GNNGuard folder, the Nettack-Di.py, Nettack-In.py, and Mettack.py corresponding to the three adversarial attacks.

For example, to check the performance of GCN without defense under direct targeted attack, run the following code:

python Nettack-Di.py --dataset Cora  --modelname GCN --GNNGuard False

Turn on the GNNGuard defense, run

python Nettack-Di.py --dataset Cora  --modelname GCN --GNNGuard True

Note: Please uncomment the defense models (Line 144 for Nettack-Di.py) to test different defense models.

Citing

If you find GNNGuard useful for your research, please consider citing this paper:

@inproceedings{zhang2020gnnguard,
title     = {GNNGuard: Defending Graph Neural Networks against Adversarial Attacks},
author    = {Zhang, Xiang and Zitnik, Marinka},
booktitle = {NeurIPS},
year      = {2020}
}

Requirements

GNNGuard is tested to work under Python >=3.5.

Recent versions of Pytorch, torch-geometric, numpy, and scipy are required. All the required basic packages can be installed using the following command: ''' pip install -r requirements.txt ''' Note: For toch-geometric and the related dependices (e.g., cluster, scatter, sparse), the higher version may work but haven't been tested yet.

Install DeepRobust

During the evaluation, the adversarial attacks on graph are performed by DeepRobust from MSU, please install it by

git clone https://github.com/DSE-MSU/DeepRobust.git
cd DeepRobust
python setup.py install
  1. If you have trouble in installing DeepRobust, please try to replace the provided 'defense/setup.py' to replace the original DeepRobust-master/setup.py and manully reinstall it by
python setup.py install
  1. We extend the original DeepRobust from single GCN to multiplye GNN variants including GAT, GIN, Jumping Knowledge, and GCN-SAINT. After installing DeepRobust, please replace the origininal folder DeepRobust-master/deeprobust/graph/defense by the defense folder that provided in our repository!

  2. To better plugin GNNGuard to geometric codes, we slightly revised some functions in geometric. Please use the three files under our provided nn/conv/ to replace the corresponding files in the installed geometric folder (for example, the folder path could be /home/username/.local/lib/python3.5/site-packages/torch_geometric/nn/conv/).

Note: 1). Don't forget to backup all the original files when you replacing anything, in case you need them at other places! 2). Please install the corresponding CUDA versions if you are using GPU.

Datasets

Here we provide the datasets (including Cora, Citeseer, ogbn-arxiv, and DP) used in GNNGuard paper.

The ogbn-arxiv dataset can be easily access by python codes:

from ogb.nodeproppred import PygNodePropPredDataset
dataset = PygNodePropPredDataset(name = 'ogbn-arxiv')

More details about ogbn-arxiv dataset can be found here.

Find more details about Disease Pathway dataset at here.

For graphs with structural roles, a prominent type of heterophily, we calculate the nodes' similarity using graphlet degree vector instead of node embedding. The graphlet degree vector is generated/counted based on the Orbit Counting Algorithm (Orca).

Miscellaneous

Please send any questions you might have about the code and/or the algorithm to [email protected].

License

GNNGuard is licensed under the MIT License.

Owner
Zitnik Lab @ Harvard
Machine Learning for Medicine and Science
Zitnik Lab @ Harvard
TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios

TPH-YOLOv5 This repo is the implementation of "TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-Captured

cv516Buaa 439 Dec 22, 2022
An architecture that makes any doodle realistic, in any specified style, using VQGAN, CLIP and some basic embedding arithmetics.

Sketch Simulator An architecture that makes any doodle realistic, in any specified style, using VQGAN, CLIP and some basic embedding arithmetics. See

12 Dec 18, 2022
Iranian Cars Detection using Yolov5s, PyTorch

Iranian Cars Detection using Yolov5 Train 1- git clone https://github.com/ultralytics/yolov5 cd yolov5 pip install -r requirements.txt 2- Dataset ../

Nahid Ebrahimian 22 Dec 05, 2022
Flexible Option Learning - NeurIPS 2021

Flexible Option Learning This repository contains code for the paper Flexible Option Learning presented as a Spotlight at NeurIPS 2021. The implementa

Martin Klissarov 7 Nov 09, 2022
Tutorial: Introduction to Graph Machine Learning, with Jupyter notebooks

GraphMLTutorialNLDL22 Tutorial NLDL22: Introduction to Graph Machine Learning, with Jupyter notebooks This tutorial takes place during the conference

UiT Machine Learning Group 3 Jan 10, 2022
EdiBERT is a generative model based on a bi-directional transformer, suited for image manipulation

EdiBERT, a generative model for image editing EdiBERT is a generative model based on a bi-directional transformer, suited for image manipulation. The

16 Dec 07, 2022
A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis

A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis This is the pytorch implementation for our MICCAI 2021 paper. A Mul

Jiarong Ye 7 Apr 04, 2022
A PyTorch Implementation of Single Shot MultiBox Detector

SSD: Single Shot MultiBox Object Detector, in PyTorch A PyTorch implementation of Single Shot MultiBox Detector from the 2016 paper by Wei Liu, Dragom

Max deGroot 4.8k Jan 07, 2023
Code for the paper "Zero-shot Natural Language Video Localization" (ICCV2021, Oral).

Zero-shot Natural Language Video Localization (ZSNLVL) by Pseudo-Supervised Video Localization (PSVL) This repository is for Zero-shot Natural Languag

Computer Vision Lab. @ GIST 37 Dec 27, 2022
A repository for interferometer controller code.

dses-interferometer-controller A repository for interferometer controller code, hardware, and simulations. See dses.science for more information on th

Eli Reed 1 Jan 17, 2022
Official PyTorch Implementation of paper EAN: Event Adaptive Network for Efficient Action Recognition

Official PyTorch Implementation of paper EAN: Event Adaptive Network for Efficient Action Recognition

TianYuan 27 Nov 07, 2022
A Multi-modal Model Chinese Spell Checker Released on ACL2021.

ReaLiSe ReaLiSe is a multi-modal Chinese spell checking model. This the office code for the paper Read, Listen, and See: Leveraging Multimodal Informa

DaDa 106 Dec 29, 2022
On the Analysis of French Phonetic Idiosyncrasies for Accent Recognition

On the Analysis of French Phonetic Idiosyncrasies for Accent Recognition With the spirit of reproducible research, this repository contains codes requ

0 Feb 24, 2022
CCCL: Contrastive Cascade Graph Learning.

CCGL: Contrastive Cascade Graph Learning This repo provides a reference implementation of Contrastive Cascade Graph Learning (CCGL) framework as descr

Xovee Xu 19 Dec 05, 2022
The official implementation of paper Siamese Transformer Pyramid Networks for Real-Time UAV Tracking, accepted by WACV22

SiamTPN Introduction This is the official implementation of the SiamTPN (WACV2022). The tracker intergrates pyramid feature network and transformer in

Robotics and Intelligent Systems Control @ NYUAD 29 Jan 08, 2023
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

AutoAugment - Learning Augmentation Policies from Data Unofficial implementation of the ImageNet, CIFAR10 and SVHN Augmentation Policies learned by Au

Philip Popien 1.3k Jan 02, 2023
Pytorch implementation of BRECQ, ICLR 2021

BRECQ Pytorch implementation of BRECQ, ICLR 2021 @inproceedings{ li&gong2021brecq, title={BRECQ: Pushing the Limit of Post-Training Quantization by Bl

Yuhang Li 148 Dec 28, 2022
PyTorch implementation of Off-policy Learning in Two-stage Recommender Systems

Off-Policy-2-Stage This repo provides a PyTorch implementation of the MovieLens experiments for the following paper: Off-policy Learning in Two-stage

Jiaqi Ma 25 Dec 12, 2022
Official PyTorch implementation of the NeurIPS 2021 paper StyleGAN3

Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation of the NeurIPS 2021 paper Alias-Free Generative Adversarial Net

Eugenio Herrera 92 Nov 18, 2022
This is the dataset and code release of the OpenRooms Dataset.

This is the dataset and code release of the OpenRooms Dataset.

Visual Intelligence Lab of UCSD 95 Jan 08, 2023