Simple and Efficient Partial Graph Adversarial Attack: A New Perspective
IEEE Transactions on Knowledge and Data Engineering · 2024-08 · 36 (8) · 4245-4259
DOI: 10.1109/tkde.2024.3364972 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2024-08. Verfasst von Guanghui Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Key R&D Program of Jiangsu Province.
Abstract (Originalsprache)
As the study of graph neural networks becomes more intensive and comprehensive, their robustness and security have received great research interest. The existing global attack methods treat all nodes in the graph as their attack targets. Although existing methods have achieved excellent results, there is still considerable space for improvement. The key problem is that the current approaches rigidly follow the definition of global attacks. They ignore an important issue, i.e., different nodes have different robustness and are not equally resilient to attacks. From a global attacker's view, we should arrange the attack budget wisely, rather than wasting them on highly robust nodes. To this end, we propose a totally new method named partial graph attack (PGA), which selects the vulnerable nodes as attack targets. First, to select the vulnerable items, we propose a hierarchical target selection policy, which allows attackers to only focus on easy-to-attack nodes. Then, we propose a cost-effective anchor-picking policy to pick the most promising anchors for adding or removing edges, and a more aggressive iterative greedy-based attack method to perform more efficient attacks. Extensive experimental results demonstrate that PGA can achieve significant improvements in both attack effect and attack efficiency compared to existing graph global attack methods.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Key R&D Program of Jiangsu Province
- Collaborative Innovation Center of Novel Software Technology and Industrialization
Zitieren
APA
Zhu, G., Chen, M., Yuan, C., & Huang, Y. (2024). Simple and Efficient Partial Graph Adversarial Attack: A New Perspective. IEEE Transactions on Knowledge and Data Engineering, 36(8), 4245-4259. https://doi.org/10.1109/tkde.2024.3364972
Vancouver
Zhu G, Chen M, Yuan C, Huang Y. Simple and Efficient Partial Graph Adversarial Attack: A New Perspective. IEEE Transactions on Knowledge and Data Engineering. 2024;36(8):4245-4259. doi:10.1109/tkde.2024.3364972
BibTeX
@article{Zhu2024,
author = {Zhu, Guanghui and Chen, Mengyu and Yuan, Chunfeng and Huang, Yihua},
title = {Simple and Efficient Partial Graph Adversarial Attack: A New Perspective},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2024},
volume = {36},
number = {8},
pages = {4245--4259},
doi = {10.1109/tkde.2024.3364972}
}
EUVIMED