---
title: "Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers"
authors:
  - "Dongyi Liu"
  - "Jiangtong Li"
doi: "10.24963/ijcai.2026/76"
url: "https://ijcai.org/proceedings/2026/76"
pdf: "https://ijcai.org/proceedings/2026/0076.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "670-678"
track: "Main Track"
keywords:
  - "Data Mining: Mining graphs"
  - "AI Ethics, Trust, Fairnes: Safety and robustness"
---

# Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers

Dongyi Liu, Jiangtong Li

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 670-678. DOI: [10.24963/ijcai.2026/76](https://doi.org/10.24963/ijcai.2026/76)

## Abstract

Graph Neural Networks (GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. 
Existing trigger generators  are often simplistic in structure and overly reliant on specific features, confining them to a single graph learning paradigm, such as graph supervised learning, graph contrastive learning, or graph prompt learning.
Such paradigm-specific designs lead to poor transferability across different learning frameworks, limiting attack success rates in general testing scenarios.
To bridge this gap, we propose Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers (CP-GBA), which employs Graph Prompt Learning (GPL) to synthesize transferable subgraph triggers. Specifically, we first distill a compact yet expressive trigger set into a queryable repository, jointly optimizing for class-awareness, feature richness, and structural fidelity. Furthermore, we pioneer the theoretical exploration of GPL transferability under prompt-based objectives, ensuring robust generalization to diverse and unseen test-time paradigms.
 Extensive experiments across multiple real-world datasets and defense scenarios show that CP-GBA achieves state-of-the-art attack success rates. Code is available at https://github.com/novdream/CP-GBA.