A novel data-level prompt injection attack against graph prompt learning
Graph Neural Networks (GNNs) are increasingly deployed in security-critical applications, including fraud detection, recommendation integrity analysis, and scientific knowledge mining. Recently, Graph Prompt Learning (GPL) has emerged as a parameter-efficient paradigm for adapting pretrained GNNs to downstream tasks. B...
Meng-Ying Yuan, Zhi-Yong Zhang, Gao-Yuan Quan et al.
· Cybersecurity · 0 citations