Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915499748622336 |
|---|---|
| author | Gao, Honglin Li, Xiang Sun, Yajuan Xiao, Gaoxi |
| author_facet | Gao, Honglin Li, Xiang Sun, Yajuan Xiao, Gaoxi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification Gao, Honglin Li, Xiang Sun, Yajuan Xiao, Gaoxi Machine Learning Artificial Intelligence 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. |
| title | Top K Enhanced Reinforcement Learning Attacks on Heterogeneous Graph Node Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.01964 |