Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
This work addresses vulnerabilities in heterogeneous graph node classification models, which is an incremental contribution to adversarial attack research in graph-based machine learning.
The paper tackles the problem of adversarial attacks on heterogeneous graph neural networks (GNNs) by proposing HeteroKRLAttack, a targeted evasion black-box method that integrates reinforcement learning with a Top-K algorithm, resulting in significant reductions in classification accuracy compared to baseline methods.
Graph Neural Networks (GNNs) have attracted substantial interest due to their exceptional performance on graph-based data. However, their robustness, especially on heterogeneous graphs, remains underexplored, particularly against adversarial attacks. This paper proposes HeteroKRLAttack, a targeted evasion black-box attack method for heterogeneous graphs. By integrating reinforcement learning with a Top-K algorithm to reduce the action space, our method efficiently identifies effective attack strategies to disrupt node classification tasks. We validate the effectiveness of HeteroKRLAttack through experiments on multiple heterogeneous graph datasets, showing significant reductions in classification accuracy compared to baseline methods. An ablation study underscores the critical role of the Top-K algorithm in enhancing attack performance. Our findings highlight potential vulnerabilities in current models and provide guidance for future defense strategies against adversarial attacks on heterogeneous graphs.