mlsanityData to 7 Oct 2026

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv 2503.09049 ↗First posted 12 Mar 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph's topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 51 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

25 of 51 references.

References · 25

  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. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  7. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  9. 2017Countering Adversarial Images using Input Transformationscited by 517
  10. 2017Representation Learning on Graphs: Methods and Applicationscited by 456
  11. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  12. 2018Adversarial Attack on Graph Structured Datacited by 300
13 more
  1. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  2. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  3. 2020Backdoor Attacks to Graph Neural Networkscited by 126
  4. 2020Graph Backdoorcited by 112
  5. 2019Meta-GNN: On Few-shot Node Classification in Graph Meta-learningcited by 105
  6. 2016Low Data Drug Discovery with One-shot Learningcited by 91
  7. 2018Model-Reuse Attacks on Deep Learning Systemscited by 47
  8. 2023Unnoticeable Backdoor Attacks on Graph Neural Networkscited by 45
  9. 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
  10. 2018Accurate, Efficient and Scalable Graph Embeddingcited by 35
  11. 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
  12. 2018Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagationcited by 14
  13. 2020Semantic-preserving Reinforcement Learning Attack Against Graph Neural Networks for Malware Detectioncited by 12

Built on by

Not cited yet.