Summary of Fedgig: Graph Inversion From Gradient in Federated Learning, by Tianzhe Xiao et al.
FedGIG: Graph Inversion from Gradient in Federated Learning
by Tianzhe Xiao, Yichen Li, Yining Qi, Haozhao Wang, Ruixuan Li
First submitted to arxiv on: 24 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper introduces a novel gradient inversion attack (GIA) method called Graph Inversion from Gradient in Federated Learning (FedGIG), specifically designed for graph-structured data in federated learning. The authors first explore the impact of GIAs on federated graph learning and demonstrate FedGIG’s superiority over existing GIA techniques through extensive experiments on molecular datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to share computer models without sharing our personal information. But some sneaky attacks can still find out what we’re trying to keep private. This paper talks about these “gradient inversion” attacks and how they affect a special kind of data called graph-structured data. The authors came up with a new way to stop these attacks, which they call FedGIG. They tested it on some really important molecular datasets and found that it works way better than the old methods. |
Keywords
* Artificial intelligence * Federated learning
