Summary of Uifv: Data Reconstruction Attack in Vertical Federated Learning, by Jirui Yang et al.
UIFV: Data Reconstruction Attack in Vertical Federated Learning
by Jirui Yang, Peng Chen, Zhihui Lu, Qiang Duan, Yubing Bao
First submitted to arxiv on: 18 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (stat.ML)
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 This paper introduces a novel approach called UIFV (Unified InverNet Framework) to enhance privacy protection in Vertical Federated Learning (VFL). Unlike existing methods that rely on gradients or model details, UIFV reconstructs original data by leveraging intermediate feature data exchanged during the inference phase of VFL. The authors demonstrate the effectiveness of their method through experiments on four datasets, showing significant improvements over state-of-the-art techniques in attack precision. The paper highlights severe privacy vulnerabilities within VFL systems, emphasizing the need for further enhancing privacy protection in practical VFL applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper talks about making sure that when people share data to work together on machine learning projects, their personal information stays private. Currently, some methods can reconstruct sensitive details from shared data, which is a problem. The authors propose a new way to keep this information safe by using the data exchanged between participants during the project. They tested their method on several datasets and showed that it works better than previous approaches in keeping things private. |
Keywords
» Artificial intelligence » Federated learning » Inference » Machine learning » Precision
