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.
| Comments: | accepted by IJCAI 2026 |
| Subjects: | Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2510.22555 [cs.CR] |
| (or arXiv:2510.22555v3 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2510.22555 arXiv-issued DOI via DataCite |
From: Dongyi Liu [view email]
[v1]
Sun, 26 Oct 2025 07:10:07 UTC (1,557 KB)
[v2]
Mon, 4 May 2026 15:48:35 UTC (1,541 KB)
[v3]
Tue, 5 May 2026 03:00:23 UTC (1,542 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。