Graph Adversarial Attack

Graph adversarial attacks explore vulnerabilities in Graph Neural Networks (GNNs), aiming to subtly alter graph structure or node features to mislead GNN predictions. Current research focuses on developing both sophisticated attack methods, such as those leveraging gradient information or eigencentrality, and robust defense mechanisms, including architectural modifications (e.g., incorporating defensive operations into the GNN design) and data augmentation techniques (e.g., homophilous augmentation). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of GNNs in various applications, from social network analysis to autonomous systems, where the consequences of erroneous predictions can be significant.

Papers

May 10, 2024

Disttack: Graph Adversarial Attacks Toward Distributed GNN Training
Yuxiang Zhang, Xin Liu, Meng Wu, Wei Yan, Mingyu Yan, Xiaochun Ye, Dongrui Fan
Graph Neural Network Adversarial Attack Gene Level GNN GNN Training Graph Adversarial Attack

April 25, 2024

Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection
Yuanchen Bei, Sheng Zhou, Jinke Shi, Yao Ma, Haishuai Wang, Jiajun Bu
Graph Neural Network Anomaly Detection Graph Anomaly Detection Anomalous Graph Graph Adversarial Attack

December 14, 2023

Towards Inductive Robustness: Distilling and Fostering Wave-induced Resonance in Transductive GCNs Against Graph Adversarial Attacks
Ao Liu, Wenshan Li, Tao Li, Beibei Li, Hanyuan Huang, Pan Zhou
Robust Learning Graph Adversarial Attack Acoustic Resonance

December 12, 2023

Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection
Jonathan J. Y. Kim, Martin Urschler, Patricia J. Riddle, Jorg S. Wicker
Adversarial Attack Visual SLAM Loop Closure Graph Adversarial Attack

August 29, 2023

Everything Perturbed All at Once: Enabling Differentiable Graph Attacks
Haoran Liu, Bokun Wang, Jianling Wang, Xiangjue Dong, Tianbao Yang, James Caverlee
Adversarial Attack Graph Model Attack Performance Gradient Based Meta Learning Graph Adversarial Attack

August 15, 2023

Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
Guanghui Zhu, Mengyu Chen, Chunfeng Yuan, Yihua Huang
New Perspective Malicious Node Graph Adversarial Attack Graph Poisoning Attack

April 9, 2023

Adversarially Robust Neural Architecture Search for Graph Neural Networks
Beini Xie, Heng Chang, Ziwei Zhang, Xin Wang, Daixin Wang, Zhiqiang Zhang, Rex Ying, Wenwu Zhu
Graph Neural Network GNN Architecture DNN Robustness Robust Graph Neural Network Graph Adversarial Attack Robust Neural Architecture Search

January 4, 2023

GUAP: Graph Universal Attack Through Adversarial Patching
Xiao Zang, Jie Chen, Bo Yuan
Adversarial Attack Graph Attention Network Adversarial Patch Attack Performance Graph Adversarial Attack Imagenet Transfer

November 15, 2022

Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation
Zhihao Zhu, Chenwang Wu, Min Zhou, Hao Liao, Defu Lian, Enhong Chen
Adversarial Attack Random Node State of the Art Defense Defense Framework Graph Adversarial Attack Graph Injection Attack Collaborative Augmentation

April 20, 2022

GUARD: Graph Universal Adversarial Defense
Jintang Li, Jie Liao, Ruofan Wu, Liang Chen, Zibin Zheng, Jiawang Dan, Changhua Meng, Weiqiang Wang
Adversarial Attack Adversarial Perturbation Graph Adversarial Attack Untargeted Adversarial Attack

March 7, 2022

Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision
Jun Zhuang, Mohammad Al Hasan
Adversarial Attack Sparse Graph Unlabeled Node Graph Adversarial Attack