mlsanityData to 14 Oct 2026

Task and Model Agnostic Adversarial Attack on Graph Neural Networks

arXiv 2112.13267 ↗First posted 25 Dec 2021cs.LG cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks on Graph Neural Networks (GNNs) reveal their security vulnerabilities, limiting their adoption in safety-critical applications. However, existing attack strategies rely on the knowledge of either the GNN model being used or the predictive task being attacked. Is this knowledge necessary? For example, a graph may be used for multiple downstream tasks unknown to a practical attacker. It is thus important to test the vulnerability of GNNs to adversarial perturbations in a model and task agnostic setting. In this work, we study this problem and show that GNNs remain vulnerable even when the downstream task and model are unknown. The proposed algorithm, TANDIS (Targeted Attack via Neighborhood DIStortion) shows that distortion of node neighborhoods is effective in drastically compromising prediction performance. Although neighborhood distortion is an NP-hard problem, TANDIS designs an effective heuristic through a novel combination of Graph Isomorphism Network with deep Q-learning. Extensive experiments on real datasets and state-of-the-art models show that, on average, TANDIS is up to 50% more effective than state-of-the-art techniques, while being more than 1000 times faster.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 25 Dec 2021.

Builds on

34 of 49 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  7. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  8. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  9. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 413
  10. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  11. 2018Adversarial Attack on Graph Structured Datacited by 301
  12. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
22 more
  1. 2019Efficient Graph Generation with Graph Recurrent Attention Networkscited by 234
  2. 2019Position-aware Graph Neural Networkscited by 203
  3. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  4. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  5. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 167
  6. 2018Adversarial Attacks on Node Embeddings via Graph Poisoningcited by 109
  7. 2016Motifs in Temporal Networkscited by 101
  8. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  9. 2020PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterestcited by 75
  10. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  11. 2020GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generationcited by 66
  12. 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
  13. 2019Data Poisoning Attack against Knowledge Graph Embeddingcited by 36
  14. 2019Attacking Graph Convolutional Networks via Rewiringcited by 32
  15. 2021GREED: A Neural Framework for Learning Graph Distance Functionscited by 32
  16. 2019A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learningcited by 31
  17. 2019Meta-Graph: Few Shot Link Prediction via Meta Learningcited by 24
  18. 2020Adversarial Attack on Community Detection by Hiding Individualscited by 20
  19. 2020Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Functioncited by 14
  20. 2021GraphAttacker: A General Multi-Task GraphAttack Frameworkcited by 8
  21. 2020Reinforcement Learning-based Black-Box Evasion Attacks to Link Prediction in Dynamic Graphscited by 6
  22. 2021Adversarial Attack on Network Embeddings via Supervised Network Poisoningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024HGAttack: Transferable Heterogeneous Graph Adversarial Attackcited by 6
  2. 2024SAGMAN: Stability Analysis of Graph Neural Networks on the Manifoldscited by 4
  3. 2024AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimizationcited by 1
  4. 2025Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defensescited by 0
  5. 2026Target-Aware Interaction-Guided Reinforcement Learning for Black-Box Node Injection Attacks on Graph Neural Networkscited by 0