FedGIG: Graph Inversion from Gradient in Federated 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_ | 1866910762123919360 |
|---|---|
| author | Xiao, Tianzhe Li, Yichen Qi, Yining Wang, Haozhao Li, Ruixuan |
| author_facet | Xiao, Tianzhe Li, Yichen Qi, Yining Wang, Haozhao Li, Ruixuan |
| contents | Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constraining module, which ensures the sparsity and discreteness of the reconstructed graph data, and the subgraph reconstruction module, which is designed to complete missing common subgraph structures. Extensive experiments on molecular datasets demonstrate FedGIG's superior accuracy over existing GIA techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18513 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FedGIG: Graph Inversion from Gradient in Federated Learning Xiao, Tianzhe Li, Yichen Qi, Yining Wang, Haozhao Li, Ruixuan Machine Learning Cryptography and Security Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constraining module, which ensures the sparsity and discreteness of the reconstructed graph data, and the subgraph reconstruction module, which is designed to complete missing common subgraph structures. Extensive experiments on molecular datasets demonstrate FedGIG's superior accuracy over existing GIA techniques. |
| title | FedGIG: Graph Inversion from Gradient in Federated Learning |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2412.18513 |