mlsanityData to 7 Oct 2026

Problem space structural adversarial attacks for Network Intrusion Detection Systems based on Graph Neural Networks

arXiv 2403.11830 ↗First posted 18 Mar 2024cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine Learning (ML) algorithms have become increasingly popular for supporting Network Intrusion Detection Systems (NIDS). Nevertheless, extensive research has shown their vulnerability to adversarial attacks, which involve subtle perturbations to the inputs of the models aimed at compromising their performance. Recent proposals have effectively leveraged Graph Neural Networks (GNN) to produce predictions based also on the structural patterns exhibited by intrusions to enhance the detection robustness. However, the adoption of GNN-based NIDS introduces new types of risks. In this paper, we propose the first formalization of adversarial attacks specifically tailored for GNN in network intrusion detection. Moreover, we outline and model the problem space constraints that attackers need to consider to carry out feasible structural attacks in real-world scenarios. As a final contribution, we conduct an extensive experimental campaign in which we launch the proposed attacks against state-of-the-art GNN-based NIDS. Our findings demonstrate the increased robustness of the models against classical feature-based adversarial attacks, while highlighting their susceptibility to structure-based attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 18 Mar 2024.

Builds on

21 of 45 references.

References · 21

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  5. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  6. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  7. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 166
  8. 2019A Restricted Black-box Adversarial Framework Towards Attacking Graph Embedding Modelscited by 68
  9. 2021E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoTcited by 55
  10. 2021Modeling Realistic Adversarial Attacks against Network Intrusion Detection Systemscited by 39
  11. 2019FENCE: Feasible Evasion Attacks on Neural Networks in Constrained Environmentscited by 23
  12. 2021threaTrace: Detecting and Tracing Host-based Threats in Node Level Through Provenance Graph Learningcited by 22
9 more
  1. 2022The Role of Machine Learning in Cybersecuritycited by 21
  2. 2020Indirect Adversarial Attacks via Poisoning Neighbors for Graph Convolutional Networkscited by 16
  3. 2021Unveiling the potential of Graph Neural Networks for robust Intrusion Detectioncited by 14
  4. 2023Black-box Adversarial Example Attack towards FCG Based Android Malware Detection under Incomplete Feature Informationcited by 13
  5. 2020Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detectioncited by 12
  6. 2020Adversarial Network Traffic: Towards Evaluating the Robustness of Deep Learning-Based Network Traffic Classificationcited by 11
  7. 2021Graph-based Solutions with Residuals for Intrusion Detection: the Modified E-GraphSAGE and E-ResGAT Algorithmscited by 11
  8. 2021Launching Adversarial Attacks against Network Intrusion Detection Systems for IoTcited by 9
  9. 2014Security Evaluation of Support Vector Machines in Adversarial Environmentscited by 8

Built on by

Not cited yet.