Summary of Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach, by Qi Tan et al.
Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
by Qi Tan, Qi Li, Yi Zhao, Zhuotao Liu, Xiaobing Guo, Ke Xu
First submitted to arxiv on: 2 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC)
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 A novel Federated Learning (FL) approach is proposed to mitigate membership inference attacks (MIA) and data reconstruction attacks (DRA), which compromise the privacy of clients in FL. The existing techniques, such as Differential Privacy (DP), are insufficient to effectively throttle DRA. This paper aims to develop a more robust FL framework that can withstand MIA and DRA. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated Learning trains models among different devices without sharing their data directly. However, this approach is vulnerable to privacy attacks. The goal of this research is to make Federated Learning safer by preventing attackers from reconstructing local datasets or inferring which clients contributed which data. |
Keywords
* Artificial intelligence * Federated learning * Inference
