Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
Not on the map. Why?
Abstract (arXiv)
Despite the success of graph neural networks (GNNs) in various domains, they exhibit susceptibility to adversarial attacks. Understanding these vulnerabilities is crucial for developing robust and secure applications. In this paper, we investigate the impact of test time adversarial attacks through edge perturbations which involve both edge insertions and deletions. A novel explainability-based method is proposed to identify important nodes in the graph and perform edge perturbation between these nodes. The proposed method is tested for node classification with three different architectures and datasets. The results suggest that introducing edges between nodes of different classes has higher impact as compared to removing edges among nodes within the same class.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 28 Dec 2023.
Builds on
28 of 37 references.
References · 28
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
- 2014DeepWalk: Online Learning of Social Representationscited by 1,547
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
16 more
- 2018Adversarial Attack on Graph Structured Datacited by 301
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2020A Note on Over-Smoothing for Graph Neural Networkscited by 249
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 167
- 2022Evaluating Explainability for Graph Neural Networkscited by 87
- 2018Fast Gradient Attack on Network Embeddingcited by 65
- 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
- 2020A Survey of Adversarial Learning on Graphscited by 42
- 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
- 2019Attacking Graph Convolutional Networks via Rewiringcited by 32
- 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 31
- 2018Attack Graph Convolutional Networks by Adding Fake Nodescited by 26
- 2020Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Modelscited by 18
- 2016Column Networks for Collective Classificationcited by 17
Built on by
Citing papers per year: 2026: 1.
1 paper.