Summary of Sok: Verifiable Cross-silo Fl, by Aleksei Korneev (cristal et al.
SoK: Verifiable Cross-Silo FL
by Aleksei Korneev, Jan Ramon
First submitted to arxiv on: 11 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); 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 This paper presents a systematization of knowledge on verifiable cross-silo Federated Learning (FL), which is a type of machine learning that trains models with data distributed across multiple devices. The focus is on moderate-sized participant groups, like hospitals or financial institutions, where malicious parties might try to disrupt the training process for personal gain. To address this issue, researchers have developed verifiable protocols that ensure parties follow the training procedure and perform computations correctly. This paper analyzes various protocols, fits them into a taxonomy, compares their efficiency and threat models, and discusses the use of Zero-Knowledge Proof (ZKP) schemes to minimize costs in a FL context. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In simple terms, this paper is about making sure that when many organizations work together to train machine learning models, nobody tries to cheat or manipulate the results. It’s like having a referee in a game who makes sure everyone plays by the rules. The paper looks at different ways to do this and compares how well they work. |
Keywords
» Artificial intelligence » Federated learning » Machine learning
