Adversarial Defense Framework for Graph Neural Network

2019-05-09 · Shen Wang, Zhengzhang Chen, Jingchao Ni, Xiao Yu, Zhichun Li, Haifeng Chen, Philip S. Yu

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities and defense GNN against the adversarial attacks? In this paper, we propose DefNet, an effective adversarial defense framework for GNNs. In particular, we first investigate the latent vulnerabilities in every layer of GNNs and propose corresponding strategies including dual-stage aggregation and bottleneck perceptron. Then, to cope with the scarcity of training data, we propose an adversarial contrastive learning method to train the GNN in a conditional GAN manner by leveraging the high-level graph representation. Extensive experiments on three public datasets demonstrate the effectiveness of DefNet in improving the robustness of popular GNN variants, such as Graph Convolutional Network and GraphSAGE, under various types of adversarial attacks.

📄 PDF Abstract BibTeX arXiv:1905.03679

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Defense Contrastive Learning Graph Neural Network Representation Learning

Methods 이 논문이 사용한 방법론

GraphSAGE GraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Dogecoin Customer Service Number +1-833-534-1729 설명 없음

DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder

2020-06-16 · Ao Zhang, Jinwen Ma

Graph neural networks (GNNs) achieve remarkable performance for tasks on graph data. However, recent works show they are extremely vulnerable to adversarial structural perturbations, making their outcomes unreliable. In …

GraphDefense: Towards Robust Graph Convolutional Networks

2019-11-11 · Xiaoyun Wang, Xuanqing Liu, Cho-Jui Hsieh

In this paper, we study the robustness of graph convolutional networks (GCNs). Despite the good performance of GCNs on graph semi-supervised learning tasks, previous works have shown that the original GCNs are very unsta…

Adversarial Defense

Adversarial Examples on Graph Data: Deep Insights into Attack and Defense

2019-03-05 · Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty 외

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversari…

Adversarial Attack Adversarial Defense

Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs

2024-06-06 · Duanyu Li, Huijun Wu, Min Xie, Xugang Wu 외

Graph neural network (GNN) models play a pivotal role in numerous tasks involving graph-related data analysis. Despite their efficacy, similar to other deep learning models, GNNs are susceptible to adversarial attacks. E…

Adversarial Defense Graph Neural Network Graph structure learning

IDEA: Invariant Defense for Graph Adversarial Robustness

2023-05-25 · Shuchang Tao, Qi Cao, HuaWei Shen, Yunfan Wu 외

Despite the success of graph neural networks (GNNs), their vulnerability to adversarial attacks poses tremendous challenges for practical applications. Existing defense methods suffer from severe performance decline unde…

Adversarial Robustness