cs.LGNov 16, 2026

GPromptShield: Elevating Resilience in Graph Prompt Tuning against Adversarial Attacks

Authors: Shuhan Song, Ping Li, Ming Dun, Maolei Huang, Huawei Cao, Xiaochun Ye

Organizations: State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Fliggy, Alibaba Group · Zhongguancun Laboratory, Beijing, China

Abstract

The paradigm of ``pre-training and prompt-tuning", with its effectiveness and lightweight characteristics, has rapidly spread from the language field to the graph field. Several pioneering studies have designed specialized prompt functions for diverse downstream graph tasks based on various graph pre-training strategies. These prompts concentrate on the compatibility between the pre-training pretext and downstream graph tasks, aiming to bridge the gap between them. However, designing prompts blindly to adapt to downstream tasks based on this concept neglects crucial security issues. By conducting covert attacks on downstream graph data, we find that even when the downstream task data closely matches that of the pre-training tasks, it is still feasible to generate highly misleading prompts using simple deceptive techniques. In this paper, we shift the primary focus of graph prompts from compatibility to vulnerability issues in adversarial attack scenarios. We design a highly extensible shield defense system for the prompts, which enhances their robustness from two perspectives: Direct Handling and Indirect Amplification. When downstream graph data contains unreliable biases, the former directly combats invalid information by incorporating hybrid multi-defense prompts to the input graph's feature space, while the latter adopts a training strategy to bypass the invalid components and amplifies valid part. We provide a theoretical derivation that proves their feasibility, indicating that unbiased prompts exist under certain conditions on unreliable data. Extensive experiments across various scenarios of adversarial attacks indicate that the prompts within our defense system exhibit enhanced resilience and superiority. This paper explores a new perspective in graph prompt learning, offering a novel option for robust prompt tuning in downstream tasks.

Figures & tables

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL

    Aug 29, 2026Shuomin Xue, Jingyuan Li, Ju Jia +2Graph Prompt LearningGraph Transfer Learning

  2. Freeze, Prompt, and Adapt: A Framework for Source-free Unsupervised GNN Prompting

    May 22, 2025Peyman Baghershahi, Sourav MedyaSource-Free Domain AdaptationUnsupervised Domain Adaptation

  3. Unified Graph Prompt Learning via Low-Rank Graph Message Prompting

    Apr 13, 2026Beibei Wang, Bo Jiang, Ziyan Zhang +1Graph Prompt LearningPrompt Learning