mlsanityData to 14 Oct 2026

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity

arXiv 2312.10943 ↗First posted 18 Dec 2023cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. However, they mainly focus on node classification tasks, neglecting the potential threats entailed within the domain of graph classification tasks. Furthermore, their practicality is questionable due to unreasonable assumptions, specifically concerning the large data requirements and extensive model knowledge. To this end, we advocate following strict settings with limited real data and hard-label awareness to generate synthetic data, thereby facilitating the stealing of the target model. Specifically, following important data generation principles, we introduce three model stealing attacks to adapt to different actual scenarios: MSA-AU is inspired by active learning and emphasizes the uncertainty to enhance query value of generated samples; MSA-AD introduces diversity based on Mixup augmentation strategy to alleviate the query inefficiency issue caused by over-similar samples generated by MSA-AU; MSA-AUD combines the above two strategies to seamlessly integrate the authenticity, uncertainty, and diversity of the generated samples. Finally, extensive experiments consistently demonstrate the superiority of the proposed methods in terms of concealment, query efficiency, and stealing performance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 55 of its 95 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

55 of 95 references.

References · 55

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  9. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  11. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  12. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
38 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  2. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  3. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  4. 2020A Survey of Deep Active Learningcited by 554
  5. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  6. 2020Label-Only Membership Inference Attackscited by 388
  7. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 321
  8. 2020GPT-GNN: Generative Pre-Training of Graph Neural Networkscited by 303
  9. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
  10. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  11. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  12. 2019High Accuracy and High Fidelity Extraction of Neural Networkscited by 214
  13. 2020Information Leakage in Embedding Modelscited by 203
  14. 2017Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2veccited by 198
  15. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  16. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 165
  17. 2018Adaptive Graph Convolutional Neural Networkscited by 155
  18. 2020Entangled Watermarks as a Defense against Model Extractioncited by 149
  19. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  20. 2017A Survey on Network Embeddingcited by 142
  21. 2018Stealing Hyperparameters in Machine Learningcited by 118
  22. 2017Topology Adaptive Graph Convolutional Networkscited by 113
  23. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  24. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 100
  25. 2015PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networkscited by 96
  26. 2019Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attackscited by 81
  27. 2020Towards More Practical Adversarial Attacks on Graph Neural Networkscited by 76
  28. 2022Towards Data-Free Model Stealing in a Hard Label Settingcited by 58
  29. 2021Adapting Membership Inference Attacks to GNN for Graph Classification: Approaches and Implicationscited by 52
  30. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  31. 2019GCN-GAN: A Non-linear Temporal Link Prediction Model for Weighted Dynamic Networkscited by 40
  32. 2020Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realizationcited by 40
  33. 2021Bag of Tricks for Node Classification with Graph Neural Networkscited by 40
  34. 2021Black-Box Attacks on Sequential Recommenders via Data-Free Model Extractioncited by 37
  35. 2021MEGEX: Data-Free Model Extraction Attack against Gradient-Based Explainable AIcited by 35
  36. 2022DualCF: Efficient Model Extraction Attack from Counterfactual Explanationscited by 32
  37. 2020Attacking Black-box Recommendations via Copying Cross-domain User Profilescited by 31
  38. 2022FP-GNN: a versatile deep learning architecture for enhanced molecular property predictioncited by 31

50 most cited of 55 All 55 (JSON)

Built on by

Not cited yet.