Let Prompts Bridge Defense Knowledge: Transferable Graph Purification via Vulnerability-Aware GPL
Artificial Intelligence
Summary
The authors worked on making Graph Neural Networks (GNNs) better at resisting attacks that try to confuse them by changing their graph data. They noticed that existing protection methods only work well within one specific type of data and take a lot of time to train. To fix this, they created ProGAP, a method that learns general patterns of attacks from large, diverse graphs and uses smart prompts to quickly adapt to new graphs without heavy retraining. Their experiments show ProGAP improves defense accuracy by up to 9% and is faster than other methods.
Graph Neural NetworksAdversarial AttacksGraph PurificationCross-domain TransferPrompt LearningTopological InformationSemantic InformationEdge DetectorRobustnessDistribution Shift
Authors
Shuomin Xue, Jingyuan Li, Ju Jia, Jingxuan Yu, Xiaojun Jia
Abstract
Graph Neural Networks (GNNs) have emerged as a cornerstone for representing complex relational dependencies in diverse multimedia tasks, particularly in cross-platform user interest modeling and cross-modal semantic alignment. In the real world, a practical defense against graph adversarial perturbations is needed. However, we observe that the prevailing adversarial purification methods are essentially domain-restricted defenses, which leads to the following shortcomings: (1) single-domain data provides insufficient structural and semantic diversity for learning robust purification criteria; (2) training of domain-specific defense strategies from scratch consumes substantial computational cost. To address the above limitations, we propose a transferable graph purification scheme, named ProGAP, to bridge adversarial defense knowledge via vulnerability-aware graph prompt learning. Firstly, to capture universal adversarial patterns, a perturbation-capture edge detector is pretrained on data-rich graphs by jointly modeling topological and semantic information. Subsequently, to achieve more knowledge transfer w.r.t. robustness, vulnerability-aware prompts are designed that inject targeted purification guidance into biased nodes, during which the pretrained detector adapts to distribution shifts in downstream graphs without parameter-laborious updates. Experimental results demonstrate that compared with state-of-the-art baselines, our ProGAP achieves 1%-9% improvement, and reduces the time consumption by up to 2.2x. The code for ProGAP is available at https://github.com/Lieyoufffff/ProGAP.