Summary of Ipfed: Identity Protected Federated Learning For User Authentication, by Yosuke Kaga et al.
IPFed: Identity protected federated learning for user authentication
by Yosuke Kaga, Yusei Suzuki, Kenta Takahashi
First submitted to arxiv on: 7 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
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 proposes a novel approach to federated learning for user authentication, which enables distributed learning without sharing personal data. The existing methods struggle to achieve both privacy preservation and high accuracy, so IPFed is developed as a solution using random projection for class embedding. Experimental results on face image datasets demonstrate that IPFed can protect the privacy of personal data while maintaining the state-of-the-art method’s accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new way to learn user authentication without sharing private information. The old methods didn’t work well, so they created something called IPFed which helps keep personal info safe and still works as well as other approaches. They tested it on face pictures and showed that it keeps the data private while keeping the results accurate. |
Keywords
» Artificial intelligence » Embedding » Federated learning
