mlsanityData to 7 Oct 2026

Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis

arXiv 2303.14836 ↗First posted 26 Mar 2023cs.LG cs.CRcited by 14

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have been utilized to create multi-layer graph models for a number of cybersecurity applications from fraud detection to software vulnerability analysis. Unfortunately, like traditional neural networks, GNNs also suffer from a lack of transparency, that is, it is challenging to interpret the model predictions. Prior works focused on specific factor explanations for a GNN model. In this work, we have designed and implemented Illuminati, a comprehensive and accurate explanation framework for cybersecurity applications using GNN models. Given a graph and a pre-trained GNN model, Illuminati is able to identify the important nodes, edges, and attributes that are contributing to the prediction while requiring no prior knowledge of GNN models. We evaluate Illuminati in two cybersecurity applications, i.e., code vulnerability detection and smart contract vulnerability detection. The experiments show that Illuminati achieves more accurate explanation results than state-of-the-art methods, specifically, 87.6% of subgraphs identified by Illuminati are able to retain their original prediction, an improvement of 10.3% over others at 77.3%. Furthermore, the explanation of Illuminati can be easily understood by the domain experts, suggesting the significant usefulness for the development of cybersecurity applications.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 37 of its 62 references that are in the map. First posted on arXiv 26 Mar 2023.

Builds on

37 of 62 references.

References · 37

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  10. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  11. 2018Link Prediction Based on Graph Neural Networkscited by 829
  12. 2015Gated Graph Sequence Neural Networkscited by 792
25 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  2. 2017Dynamic Routing Between Capsulescited by 689
  3. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  4. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  5. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  6. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  7. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  8. 2019Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networkscited by 266
  9. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  10. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  11. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  12. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  13. 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 202
  14. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  15. 2017Interpretable Convolutional Neural Networkscited by 161
  16. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  17. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  18. 2020Dos and Don'ts of Machine Learning in Computer Securitycited by 98
  19. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 95
  20. 2016Quasi-Recurrent Neural Networkscited by 87
  21. 2020Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detectioncited by 81
  22. 2017Neural Network-based Graph Embedding for Cross-Platform Binary Code Similarity Detectioncited by 65
  23. 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
  24. 2019Evaluating Explanation Methods for Deep Learning in Securitycited by 38
  25. 2017Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networkscited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 6; 2026: 3.

14 papers.

Sort:

  1. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  2. 2024Use of Graph Neural Networks in Aiding Defensive Cyber Operationscited by 7
  3. 2024Valid Conformal Prediction for Dynamic GNNscited by 6
  4. 2024Harnessing Collective Structure Knowledge in Data Augmentation for Graph Neural Networkscited by 2
  5. 2026Cybersecurity is the True Frontier for Generative AI Success or Failurecited by 2
  6. 2025Deal: Distributed End-to-End GNN Inference for All Nodescited by 1
  7. 2025Heterogeneous Graph Prompt Learning via Adaptive Weight Pruningcited by 1
  8. 2024Valid Bootstraps for Network Embeddings with Applications to Network Visualisationcited by 0
  9. 2025Interpreting Graph Inference with Skyline Explanationscited by 0
  10. 2025PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websitescited by 0
  11. 2025Fixed-point graph convolutional networks against adversarial attackscited by 0
  12. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
2 more
  1. 2026Spatio-Temporal Attention Graph Neural Network: Explaining Causalities With Attentioncited by 0
  2. 2026Graph neural networks at war: integrating cybersecurity and drone intelligence in the Israeli-Iranian conflictcited by 0