A clean-label graph backdoor attack method in node classification task
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909058175336448 |
|---|---|
| author | Xing, Xiaogang Xu, Ming Bai, Yujing Yang, Dongdong |
| author_facet | Xing, Xiaogang Xu, Ming Bai, Yujing Yang, Dongdong |
| contents | Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a clean-label graph backdoor attack method(CGBA) in the node classification task is proposed in this paper. Differently from existing backdoor attack methods, CGBA requires neither modification of node labels nor graph structure. Specifically, to solve the problem of inconsistency between the contents and labels of the samples, CGBA selects poisoning samples in a specific target class and uses the label of sample as the target label (i.e., clean-label) after injecting triggers into the target samples. To guarantee the similarity of neighboring nodes, the raw features of the nodes are elaborately picked as triggers to further improve the concealment of the triggers. Extensive experiments results show the effectiveness of our method. When the poisoning rate is 0.04, CGBA can achieve an average attack success rate of 87.8%, 98.9%, 89.1%, and 98.5%, respectively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00163 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A clean-label graph backdoor attack method in node classification task Xing, Xiaogang Xu, Ming Bai, Yujing Yang, Dongdong Cryptography and Security Machine Learning Backdoor attacks in the traditional graph neural networks (GNNs) field are easily detectable due to the dilemma of confusing labels. To explore the backdoor vulnerability of GNNs and create a more stealthy backdoor attack method, a clean-label graph backdoor attack method(CGBA) in the node classification task is proposed in this paper. Differently from existing backdoor attack methods, CGBA requires neither modification of node labels nor graph structure. Specifically, to solve the problem of inconsistency between the contents and labels of the samples, CGBA selects poisoning samples in a specific target class and uses the label of sample as the target label (i.e., clean-label) after injecting triggers into the target samples. To guarantee the similarity of neighboring nodes, the raw features of the nodes are elaborately picked as triggers to further improve the concealment of the triggers. Extensive experiments results show the effectiveness of our method. When the poisoning rate is 0.04, CGBA can achieve an average attack success rate of 87.8%, 98.9%, 89.1%, and 98.5%, respectively. |
| title | A clean-label graph backdoor attack method in node classification task |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2401.00163 |