Summary of Survey Of Privacy Threats and Countermeasures in Federated Learning, by Masahiro Hayashitani et al.
Survey of Privacy Threats and Countermeasures in Federated Learning
by Masahiro Hayashitani, Junki Mori, Isamu Teranishi
First submitted to arxiv on: 1 Feb 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 Machine learning researchers have long touted federated learning as a privacy-aware method due to its lack of direct data exchange. However, despite this apparent safeguard, privacy threats do exist. This paper provides a comprehensive cataloging of common and unique privacy risks in three typical types of federated learning: horizontal, vertical, and transfer. The authors not only identify these threats but also explore corresponding countermeasures to ensure the confidentiality and integrity of sensitive information. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way for many devices to learn together without sharing their personal data. While it seems like a great idea for keeping things private, there are actually some risks involved. This new study takes a close look at three main types of federated learning and the potential problems that come with each one. The authors hope to help developers create more secure and trustworthy models. |
Keywords
* Artificial intelligence * Federated learning * Machine learning
