This repository aims to provide links to works about adversarial attacks on graph data. It is divided into 3 parts,
- Adversarial Attacks
- Defense (Robust Traing/ Robust GCN)
- Survey
-
Multiscale Evolutionary Perturbation Attack on Community Detection. arxiv 2019. [paper]
Jinyin Chen, Yixian Chen, Lihong Chen, Minghao Zhao, and Qi Xuan.
-
A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning. NeurIPS 2019. [paper]
Xuanqing Liu, Si Si, Xiaojin(Jerry) Zhu, Yang Li, Cho-Jui Hsieh.
-
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense. IJCAI 2019. [paper]
Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu.
-
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. ICJAI 2019. [paper]
Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin.
-
Adversarial Attacks on Node Embeddings via Graph Poisoning. ICML 2019. [paper] [code]
Aleksandar Bojchevski, Stephan Günnemann.
-
Adversarial Attacks on Graph Neural Networks via Meta Learning. ICLR 2019. [paper] [code]
Daniel Zugner, Stephan Gunnemann.
-
Attacking Graph Convolutional Networks via Rewiring. arxiv 2019. [paper]
Yao Ma, Suhang Wang, Lingfei Wu, Jiliang Tang.
-
The General Black-box Attack Method for Graph Neural Networks. arxiv 2019. [paper]
Heng Chang, Yu Rong, Tingyang Xu, Wenbing Huang, Honglei Zhang, Peng Cui, Wenwu Zhu, Junzhou Huang.
-
Adversarial Attack on Graph Structured Data. ICML 2018. [paper] [code]
Hanjun Dai, Hui Li, Tian Tian, Xin Huang, Lin Wang, Jun Zhu, Le Song.
-
Adversarial Attacks on Neural Networks for Graph Data. KDD 2018. [paper] [code]
Daniel Zügner, Amir Akbarnejad, Stephan Günnemann.
-
GraphDefense: Towards Robust Graph Convolutional Networks. Arxiv 2019. [paper]
Xiaoyun Wang, Xuanqing Liu, Cho-Jui Hsieh.
-
All You Need is Low (Rank): Defending Against Adversarial Attacks on Graphs. WSDM 2020.
Negin Entezari, Saba Al-Sayouri, Amirali Darvishzadeh, and Evangelos E. Papalexakis.
-
Certifiable Robustness to Graph Perturbations. NeurIPS 2019. [paper][code]
Aleksandar Bojchevski, Stephan Günnemann.
-
Edge Dithering for Robust Adaptive Graph Convolutional Networks. arxiv 2019. [paper]
Vassilis N. Ioannidis, Georgios B. Giannakis.
-
GraphSAC: Detecting anomalies in large-scale graphs. arxiv 2019. [paper]
Vassilis N. Ioannidis, Dimitris Berberidis, Georgios B. Giannakis.
-
Robust Graph Neural Network Against Poisoning Attacks via Transfer Learning. WSDM 2020. [paper]
Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao, Prasenjit Mitra, Suhang Wang.
-
Robust Graph Convolutional Networks Against Adversarial Attacks. KDD 2019. [paper]
Dingyuan Zhu, Ziwei Zhang, Peng Cui, Wenwu Zhu.
-
Certifiable Robustness and Robust Training for Graph Convolutional Networks. KDD 2019. [paper] [code]
Daniel Zügner Stephan Günnemann.
-
Adversarial Examples on Graph Data: Deep Insights into Attack and Defense. IJCAI 2019. [paper]
Huijun Wu, Chen Wang, Yuriy Tyshetskiy, Andrew Docherty, Kai Lu, Liming Zhu.
-
Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective. ICJAI 2019. [paper]
Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin.
-
Power up! Robust Graph Convolutional Network against Evasion Attacks based on Graph Powering. arxiv 2019. [paper]
Ming Jin, Heng Chang, Wenwu Zhu, Somayeh Sojoudi.
-
Latent Adversarial Training of Graph Convolution Networks ICML 2019 workshop. [paper]
Hongwei Jin, Xinhua Zhang.
-
Batch Virtual Adversarial Training for Graph Convolutional Networks. ICML 2019 Workshop. [paper]
Zhijie Deng, Yinpeng Dong, Jun Zhu.
-
Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure. arXiv, 2019. [paper]
Fuli Feng, Xiangnan He, Jie Tang, Tat-Seng Chua.