mlsanityData to 7 Oct 2026

HeteroBA: A Structure-Manipulating Backdoor Attack on Heterogeneous Graphs

arXiv 2505.21140 ↗First posted 27 May 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Heterogeneous graph neural networks (HGNNs) have recently drawn increasing attention for modeling complex multi-relational data in domains such as recommendation, finance, and social networks. While existing research has been largely focused on enhancing HGNNs' predictive performance, their robustness and security, especially under backdoor attacks, remain underexplored. In this paper, we propose a novel Heterogeneous Backdoor Attack (HeteroBA) framework for node classification tasks on heterogeneous graphs. HeteroBA inserts carefully crafted trigger nodes with realistic features and targeted structural connections, leveraging attention-based and clustering-based strategies to select influential auxiliary nodes for effective trigger propagation, thereby causing the model to misclassify specific nodes into a target label while maintaining accuracy on clean data. Experimental results on three datasets and various HGNN architectures demonstrate that HeteroBA achieves high attack success rates with minimal impact on the clean accuracy. Our method sheds light on potential vulnerabilities in HGNNs and calls for more robust defenses against backdoor threats in multi-relational graph scenarios.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 46 references that are in the map. First posted on arXiv 27 May 2025.

Builds on

19 of 46 references.

References · 19

  1. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  2. 2019Heterogeneous Graph Attention Networkcited by 732
  3. 2020Heterogeneous Graph Transformercited by 581
  4. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  5. 2020MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embeddingcited by 304
  6. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  7. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  8. 2020Graph Backdoorcited by 112
  9. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  10. 2023Temporal and Heterogeneous Graph Neural Network for Financial Time Series Predictioncited by 30
  11. 2024Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspectivecited by 22
  12. 2023Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendationcited by 18
7 more
  1. 2023Efficient Heterogeneous Graph Learning via Random Projectioncited by 16
  2. 2022A Survey on Backdoor Attack and Defense in Natural Language Processingcited by 13
  3. 2023A clean-label graph backdoor attack method in node classification taskcited by 10
  4. 2024Robustness Inspired Graph Backdoor Defensecited by 7
  5. 2023Link Prediction on Latent Heterogeneous Graphscited by 5
  6. 2024Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpointcited by 5
  7. 2024Generalized Graph Signal Reconstruction via the Uncertainty Principlecited by 2

Built on by

Not cited yet.