Can I read Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning on EtoBox?

Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning by Ju, Mingxuan; Fan, Yujie; Zhang, Chuxu; Ye, Yanfang is a scholarly article available to read on EtoBox.

What is Let Graph be the Go Board: Gradient-free Node Injection Attack for Graph Neural Networks via Reinforcement Learning about?

Graph Neural Networks (GNNs) have drawn significant attentions over the years and been broadly applied to essential applications requiring solid robustness or vigorous security standards, such as product recommendation and user behavior modeling. Under these scenarios, exploiting GNN's vulnerabilities and further downgrading its performance become extremely incentive for adversaries. Previous attackers mainly focus on structural perturbations or node injections to the existing graphs, guided by gradients from the surrogate models. Although they deliver promising results, several limitations still exist. For the structural perturbation attack, to launch a proposed attack, adversaries need to manipulate the existing graph topology, which is impractical in most circumstances. Whereas for the node injection attack, though being more practical, current approaches require training surrogate models to simulate a white-box setting, which results in significant performance downgrade when the surrogate architecture diverges from the actual victim model. To bridge these gaps, in this paper, we study the problem of black-box node injection attack, without training a potentially misleading surr

Author

Ju, Mingxuan; Fan, Yujie; Zhang, Chuxu; Ye, Yanfang

Published

2022

Language

EN