mlsanityData to 7 Oct 2026

Finding MNEMON: Reviving Memories of Node Embeddings

arXiv 2204.06963 ↗First posted 14 Apr 2022cs.LG cs.CR stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks. Little attention has been paid to understand the privacy risks of integrating the output from graph embedding models (e.g., node embeddings) with complex downstream machine learning pipelines. In this paper, we fill this gap and propose a novel model-agnostic graph recovery attack that exploits the implicit graph structural information preserved in the embeddings of graph nodes. We show that an adversary can recover edges with decent accuracy by only gaining access to the node embedding matrix of the original graph without interactions with the node embedding models. We demonstrate the effectiveness and applicability of our graph recovery attack through extensive experiments.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 91 references that are in the map. First posted on arXiv 14 Apr 2022.

Builds on

45 of 91 references.

References · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  6. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  9. 2016Complex Embeddings for Simple Link Predictioncited by 897
  10. 2018Link Prediction Based on Graph Neural Networkscited by 829
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  12. 2019Federated Machine Learning: Concept and Applicationscited by 409
33 more
  1. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 266
  2. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
  3. 2016Molecular Graph Convolutions: Moving Beyond Fingerprintscited by 238
  4. 2019Learning Discrete Structures for Graph Neural Networkscited by 228
  5. 2020Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscited by 212
  6. 2019Stochastic Beams and Where to Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacementcited by 205
  7. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 197
  8. 2017Graph Embedding Techniques, Applications, and Performance: A Surveycited by 188
  9. 2020When Machine Unlearning Jeopardizes Privacycited by 181
  10. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  11. 2017Machine Learning Models that Remember Too Muchcited by 165
  12. 2016How to learn a graph from smooth signalscited by 146
  13. 2018DeepInf: Social Influence Prediction with Deep Learningcited by 128
  14. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  15. 2020Stealing Links from Graph Neural Networkscited by 114
  16. 2020Graph Backdoorcited by 112
  17. 2019Graph Normalizing Flowscited by 103
  18. 2017Network Representation Learning: A Surveycited by 101
  19. 2021Sequential Recommendation with Graph Neural Networkscited by 89
  20. 2020Differentiable Graph Module (DGM) for Graph Convolutional Networkscited by 86
  21. 2020Quantifying Privacy Leakage in Graph Embeddingcited by 82
  22. 2021LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysiscited by 65
  23. 2021Membership Inference Attacks Against Recommender Systemscited by 52
  24. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  25. 2019NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorizationcited by 48
  26. 2013Clustering and Community Detection in Directed Networks: A Surveycited by 38
  27. 2021Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputscited by 18
  28. 2020Simple and Effective Graph Autoencoders with One-Hop Linear Modelscited by 17
  29. 2020Little Ball of Fur: A Python Library for Graph Samplingcited by 15
  30. 2018Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagationcited by 14
  31. 2016Network structure, metadata and the prediction of missing nodes and annotationscited by 8
  32. 2021DeepWalking Backwards: From Embeddings Back to Graphscited by 6
  33. 2020Spikyball sampling: Exploring large networks via an inhomogeneous filtered diffusioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2023DPMLBench: Holistic Evaluation of Differentially Private Machine Learningcited by 13
  2. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  3. 2026Inference Attacks Against Graph Generative Diffusion Modelscited by 2
  4. 2024Towards Deeper Understanding of PPR-based Embedding Approaches: A Topological Perspectivecited by 0