Graphfool: Targeted Label Adversarial Attack on Graph Embedding
Not on the map. Why?
Abstract (arXiv)
Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional representations for vertices or edges in the graph, usually employs deep models to derive the embedding vector. However, these models are vulnerable. We envision that graph embedding methods based on deep models can be easily attacked using adversarial examples. Thus, in this paper, we propose Graphfool, a novel targeted label adversarial attack on graph embedding. It can generate adversarial graph to attack graph embedding methods via classifying boundary and gradient information in graph convolutional network (GCN). Specifically, we perform the following steps: 1),We first estimate the classification boundaries of different classes. 2), We calculate the minimal perturbation matrix to misclassify the attacked vertex according to the target classification boundary. 3), We modify the adjacency matrix according to the maximal absolute value of the disturbance matrix. This process is implemented iteratively. To the best of our knowledge, this is the first targeted label attack technique. The experiments on real-world graph networks demonstrate that Graphfool can derive better performance than state-of-art techniques. Compared with the second best algorithm, Graphfool can achieve an average improvement of 11.44% in attack success rate.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 47 of its 90 references that are in the map. First posted on arXiv 24 Feb 2021.
Builds on
47 of 90 references.
References · 47
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2017Non-local Neural Networkscited by 2,290
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
- 2014DeepWalk: Online Learning of Social Representationscited by 1,543
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
35 more
- 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2016Universal adversarial perturbationscited by 774
- 2015LINE: Large-scale Information Network Embeddingcited by 582
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
- 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
- 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
- 2018Adversarial Attack on Graph Structured Datacited by 300
- 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
- 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
- 2017Graph Embedding Techniques, Applications, and Performance: A Surveycited by 188
- 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
- 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
- 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
- 2018Adversarial Attacks and Defences Competitioncited by 96
- 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
- 2016Hiding Individuals and Communities in a Social Networkcited by 77
- 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
- 2018Fast Gradient Attack on Network Embeddingcited by 65
- 2019Certifiable Robustness to Graph Perturbationscited by 62
- 2017Security Evaluation of Pattern Classifiers under Attackcited by 39
- 2020Adversarial Attack on Large Scale Graphcited by 39
- 2018Attack Graph Convolutional Networks by Adding Fake Nodescited by 26
- 2019Adversarial Training Methods for Network Embeddingcited by 26
- 2018Data Poisoning Attack against Unsupervised Node Embedding Methodscited by 19
- 2016Column Networks for Collective Classificationcited by 17
- 2020Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networkscited by 16
- 2019Node Injection Attacks on Graphs via Reinforcement Learningcited by 15
- 2018GA Based Q-Attack on Community Detectioncited by 13
- 2019Virtual Adversarial Training on Graph Convolutional Networks in Node Classificationcited by 11
- 2018Link Prediction Adversarial Attackcited by 6
- 2018Attack Tolerance of Link Prediction Algorithms: How to Hide Your Relations in a Social Networkcited by 2
- 2019Generalizable Adversarial Attacks with Latent Variable Perturbation Modellingcited by 2
- 2018Attacking Similarity-Based Link Prediction in Social Networkscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.