Backdoor Attack on Vertical Federated Graph Neural Network Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917901320060928 |
|---|---|
| author | Yang, Jirui Chen, Peng Lu, Zhihui Deng, Ruijun Duan, Qiang Zeng, Jianping |
| author_facet | Yang, Jirui Chen, Peng Lu, Zhihui Deng, Ruijun Duan, Qiang Zeng, Jianping |
| contents | Federated Graph Neural Network (FedGNN) integrate federated learning (FL) with graph neural networks (GNNs) to enable privacy-preserving training on distributed graph data. Vertical Federated Graph Neural Network (VFGNN), a key branch of FedGNN, handles scenarios where data features and labels are distributed among participants. Despite the robust privacy-preserving design of VFGNN, we have found that it still faces the risk of backdoor attacks, even in situations where labels are inaccessible. This paper proposes BVG, a novel backdoor attack method that leverages multi-hop triggers and backdoor retention, requiring only four target-class nodes to execute effective attacks. Experimental results demonstrate that BVG achieves nearly 100% attack success rates across three commonly used datasets and three GNN models, with minimal impact on the main task accuracy. We also evaluated various defense methods, and the BVG method maintained high attack effectiveness even under existing defenses. This finding highlights the need for advanced defense mechanisms to counter sophisticated backdoor attacks in practical VFGNN applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11290 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Backdoor Attack on Vertical Federated Graph Neural Network Learning Yang, Jirui Chen, Peng Lu, Zhihui Deng, Ruijun Duan, Qiang Zeng, Jianping Machine Learning Artificial Intelligence Cryptography and Security Federated Graph Neural Network (FedGNN) integrate federated learning (FL) with graph neural networks (GNNs) to enable privacy-preserving training on distributed graph data. Vertical Federated Graph Neural Network (VFGNN), a key branch of FedGNN, handles scenarios where data features and labels are distributed among participants. Despite the robust privacy-preserving design of VFGNN, we have found that it still faces the risk of backdoor attacks, even in situations where labels are inaccessible. This paper proposes BVG, a novel backdoor attack method that leverages multi-hop triggers and backdoor retention, requiring only four target-class nodes to execute effective attacks. Experimental results demonstrate that BVG achieves nearly 100% attack success rates across three commonly used datasets and three GNN models, with minimal impact on the main task accuracy. We also evaluated various defense methods, and the BVG method maintained high attack effectiveness even under existing defenses. This finding highlights the need for advanced defense mechanisms to counter sophisticated backdoor attacks in practical VFGNN applications. |
| title | Backdoor Attack on Vertical Federated Graph Neural Network Learning |
| topic | Machine Learning Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2410.11290 |