mlsanityData to 14 Oct 2026

GraphAttacker: A General Multi-Task GraphAttack Framework

arXiv 2101.06855 ↗First posted 18 Jan 2021cs.LG cs.CRcited by 8

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have been successfully exploited in graph analysis tasks in many real-world applications. The competition between attack and defense methods also enhances the robustness of GNNs. In this competition, the development of adversarial training methods put forward higher requirement for the diversity of attack examples. By contrast, most attack methods with specific attack strategies are difficult to satisfy such a requirement. To address this problem, we propose GraphAttacker, a novel generic graph attack framework that can flexibly adjust the structures and the attack strategies according to the graph analysis tasks. GraphAttacker generates adversarial examples through alternate training on three key components: the multi-strategy attack generator (MAG), the similarity discriminator (SD), and the attack discriminator (AD), based on the generative adversarial network (GAN). Furthermore, we introduce a novel similarity modification rate SMR to conduct a stealthier attack considering the change of node similarity distribution. Experiments on various benchmark datasets demonstrate that GraphAttacker can achieve state-of-the-art attack performance on graph analysis tasks of node classification, graph classification, and link prediction, no matter the adversarial training is conducted or not. Moreover, we also analyze the unique characteristics of each task and their specific response in the unified attack framework. The project code is available at https://github.com/honoluluuuu/GraphAttacker.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 51 of its 95 references that are in the map. First posted on arXiv 18 Jan 2021.

Builds on

51 of 95 references.

References · 51

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  6. 2016Variational Graph Auto-Encoderscited by 1,382
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  8. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  9. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  10. 2015LINE: Large-scale Information Network Embeddingcited by 582
  11. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
  12. 2019Self-Attention Graph Poolingcited by 421
38 more
  1. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  2. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 371
  3. 2018Adversarial Attack on Graph Structured Datacited by 301
  4. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  5. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  6. 2020Backdoor Attacks to Graph Neural Networkscited by 128
  7. 2017GraphGAN: Graph Representation Learning with Generative Adversarial Netscited by 121
  8. 2020AM-GCN: Adaptive Multi-channel Graph Convolutional Networkscited by 121
  9. 2020Graph Backdoorcited by 112
  10. 2018Billion-scale Commodity Embedding for E-commerce Recommendation in Alibabacited by 105
  11. 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
  12. 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
  13. 2016Hiding Individuals and Communities in a Social Networkcited by 77
  14. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  15. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  16. 2018Fast Gradient Attack on Network Embeddingcited by 65
  17. 2019Certifiable Robustness to Graph Perturbationscited by 62
  18. 2019Transferring Robustness for Graph Neural Network Against Poisoning Attackscited by 58
  19. 2019Who Are the Phishers? Phishing Scam Detection on Ethereum via Network Embeddingcited by 39
  20. 2020Adversarial Attack on Large Scale Graphcited by 39
  21. 2018Attack Graph Convolutional Networks by Adding Fake Nodescited by 26
  22. 2019Adversarial Training Methods for Network Embeddingcited by 26
  23. 2015Community Detection and Classification in Hierarchical Stochastic Blockmodelscited by 23
  24. 2019T-EDGE: Temporal WEighted MultiDiGraph Embedding for Ethereum Transaction Network Analysiscited by 19
  25. 2020Graph Universal Adversarial Attacks: A Few Bad Actors Ruin Graph Learning Modelscited by 18
  26. 2020Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networkscited by 16
  27. 2018GA Based Q-Attack on Community Detectioncited by 13
  28. 2020Adversarial Attack on Hierarchical Graph Pooling Neural Networkscited by 13
  29. 2018Learning to Multitaskcited by 11
  30. 2019Virtual Adversarial Training on Graph Convolutional Networks in Node Classificationcited by 11
  31. 2019GraphSAC: Detecting anomalies in large-scale graphscited by 11
  32. 2019Can Adversarial Network Attack be Defended?cited by 10
  33. 2019Time-aware Gradient Attack on Dynamic Network Link Predictioncited by 10
  34. 2020A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settingscited by 8
  35. 2018Link Prediction Adversarial Attackcited by 6
  36. 2018Adversarial Recommendation: Attack of the Learned Fake Userscited by 5
  37. 2019Heterogeneous Graph Matching Networkscited by 5
  38. 2019De-Health: All Your Online Health Information Are Belong to Uscited by 2

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 3; 2024: 1.

8 papers.

  1. 2022Motif-Backdoor: Rethinking the Backdoor Attack on Graph Neural Networks via Motifscited by 19
  2. 2022Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classificationcited by 8
  3. 2023Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systemscited by 6
  4. 2021Adversarial Attacks on Graph Classification via Bayesian Optimisationcited by 5
  5. 2021Task and Model Agnostic Adversarial Attack on Graph Neural Networkscited by 5
  6. 2023Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detectioncited by 0
  7. 2023Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detectioncited by 0
  8. 2024Query-Efficient Adversarial Attack Against Vertical Federated Graph Learningcited by 0