mlsanityData to 7 Oct 2026

Safety in Graph Machine Learning: Threats and Safeguards

arXiv 2405.11034 ↗First posted 17 May 2024cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Graph Machine Learning (Graph ML) has witnessed substantial advancements in recent years. With their remarkable ability to process graph-structured data, Graph ML techniques have been extensively utilized across diverse applications, including critical domains like finance, healthcare, and transportation. Despite their societal benefits, recent research highlights significant safety concerns associated with the widespread use of Graph ML models. Lacking safety-focused designs, these models can produce unreliable predictions, demonstrate poor generalizability, and compromise data confidentiality. In high-stakes scenarios such as financial fraud detection, these vulnerabilities could jeopardize both individuals and society at large. Therefore, it is imperative to prioritize the development of safety-oriented Graph ML models to mitigate these risks and enhance public confidence in their applications. In this survey paper, we explore three critical aspects vital for enhancing safety in Graph ML: reliability, generalizability, and confidentiality. We categorize and analyze threats to each aspect under three headings: model threats, data threats, and attack threats. This novel taxonomy guides our review of effective strategies to protect against these threats. Our systematic review lays a groundwork for future research aimed at developing practical, safety-centered Graph ML models. Furthermore, we highlight the significance of safe Graph ML practices and suggest promising avenues for further investigation in this crucial area.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 166 of its 262 references that are in the map. First posted on arXiv 17 May 2024.

Builds on

166 of 262 references.

References · 166

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2016Deep Learning with Differential Privacycited by 2,682
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  9. 2019Invariant Risk Minimizationcited by 1,832
  10. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  11. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  12. 2016Variational Graph Auto-Encoderscited by 1,373
38 more
  1. 2019Machine Unlearningcited by 1,020
  2. 2019Attention is not Explanationcited by 916
  3. 2013Domain Generalization via Invariant Feature Representationcited by 622
  4. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  5. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  6. 2017Interpretation of Neural Networks is Fragilecited by 443
  7. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  8. 2018Deep Learning on Graphs: A Surveycited by 393
  9. 2020Environment Inference for Invariant Learningcited by 306
  10. 2018Adversarial Attack on Graph Structured Datacited by 300
  11. 2021Unsolved Problems in ML Safetycited by 291
  12. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 285
  13. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  14. 2018Scalable and accurate deep learning for electronic health recordscited by 275
  15. 2019Adversarial Attacks on Graph Neural Networks via Meta Learningcited by 261
  16. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  17. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  18. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  19. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  20. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  21. 2021Trustworthy AI: From Principles to Practicescited by 206
  22. 2021Adversarial Graph Augmentation to Improve Graph Contrastive Learningcited by 200
  23. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  24. 2020Invariant Risk Minimization Gamescited by 188
  25. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 186
  26. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  27. 2014Graph-based Anomaly Detection and Description: A Surveycited by 182
  28. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  29. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  30. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  31. 2022Handling Distribution Shifts on Graphs: An Invariance Perspectivecited by 163
  32. 2022Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphscited by 144
  33. 2022GOOD: A Graph Out-of-Distribution Benchmarkcited by 140
  34. 2021Subgraph Federated Learning with Missing Neighbor Generationcited by 132
  35. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  36. 2021Graph Unlearningcited by 129
  37. 2022Zero-Shot Machine Unlearningcited by 125
  38. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118

50 most cited of 166 All 166 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 2.

11 papers.

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2024CEB: Compositional Evaluation Benchmark for Fairness in Large Language Modelscited by 17
  3. 2025ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networkscited by 8
  4. 2025A Survey of Model Extraction Attacks and Defenses in Distributed Computing Environmentscited by 5
  5. 2024Federated Graph Learning with Graphless Clientscited by 3
  6. 2024Virtual Nodes Can Help: Tackling Distribution Shifts in Federated Graph Learningcited by 3
  7. 2025Enhancing Distribution and Label Consistency for Graph Out-of-Distribution Generalizationcited by 2
  8. 2025Generative Risk Minimization for Out-of-Distribution Generalization on Graphscited by 2
  9. 2025FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphscited by 1
  10. 2026Generalizing GNNs with Tokenized Mixture of Expertscited by 1
  11. 2026On the Safety of Graph Representation Learningcited by 0