mlsanityData to 7 Oct 2026

FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification

arXiv 2210.13815 ↗First posted 25 Oct 2022cs.LG cs.CR cs.SIcited by 7

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are vulnerable to data poisoning attacks, which will generate a poisoned graph as the input to the GNN models. We present FocusedCleaner as a poisoned graph sanitizer to effectively identify the poison injected by attackers. Specifically, FocusedCleaner provides a sanitation framework consisting of two modules: bi-level structural learning and victim node detection. In particular, the structural learning module will reverse the attack process to steadily sanitize the graph while the detection module provides ``the focus" -- a narrowed and more accurate search region -- to structural learning. These two modules will operate in iterations and reinforce each other to sanitize a poisoned graph step by step. As an important application, we show that the adversarial robustness of GNNs trained over the sanitized graph for the node classification task is significantly improved. Extensive experiments demonstrate that FocusedCleaner outperforms the state-of-the-art baselines both on poisoned graph sanitation and improving robustness.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 34 of its 74 references that are in the map. First posted on arXiv 25 Oct 2022.

Builds on

34 of 74 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2018Link Prediction Based on Graph Neural Networkscited by 829
  9. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  10. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  11. 2018Adversarial Attack on Graph Structured Datacited by 300
  12. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
22 more
  1. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  2. 2020Data Augmentation for Graph Neural Networkscited by 200
  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. 2020Graph Backdoorcited by 112
  6. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  7. 2020Strong Data Augmentation Sanitizes Poisoning and Backdoor Attacks Without an Accuracy Tradeoffcited by 86
  8. 2021Elastic Graph Neural Networkscited by 67
  9. 2021Local Augmentation for Graph Neural Networkscited by 52
  10. 2018Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detectioncited by 43
  11. 2021Understanding Structural Vulnerability in Graph Convolutional Networkscited by 37
  12. 2022Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNNcited by 34
  13. 2022Metropolis-Hastings Data Augmentation for Graph Neural Networkscited by 30
  14. 2020Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothingcited by 29
  15. 2020Adversarial Attack on Community Detection by Hiding Individualscited by 20
  16. 2021Graph Sanitation with Application to Node Classificationcited by 20
  17. 2017Supervised Community Detection with Line Graph Neural Networkscited by 18
  18. 2018Network Enhancement: a general method to denoise weighted biological networkscited by 15
  19. 2021Mask-GVAE: Blind Denoising Graphs via Partitioncited by 9
  20. 2021BinarizedAttack: Structural Poisoning Attacks to Graph-based Anomaly Detectioncited by 8
  21. 2019Multiscale Evolutionary Perturbation Attack on Community Detectioncited by 5
  22. 2019Adversarial Robustness of Similarity-Based Link Predictioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 2; 2026: 1.

7 papers.

  1. 2024Understanding the Robustness of Graph Neural Networks against Adversarial Attackscited by 1
  2. 2025AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothingcited by 1
  3. 2023Robust Graph Contrastive Learning with Information Restorationcited by 0
  4. 2024Adversarial Robustness of Link Sign Prediction in Signed Graphscited by 0
  5. 2024SFR-GNN: Simple and Fast Robust GNNs against Structural Attackscited by 0
  6. 2025Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systemscited by 0
  7. 2026GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attackscited by 0