Summary of End-to-end Verifiable Decentralized Federated Learning, by Chaehyeon Lee et al.
End-to-End Verifiable Decentralized Federated Learning
by Chaehyeon Lee, Jonathan Heiss, Stefan Tai, James Won-Ki Hong
First submitted to arxiv on: 19 Apr 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 verifiable decentralized federated learning system combining blockchains and zero-knowledge proofs (ZKP) makes local learning and global aggregation verifiable, but data can still be corrupted before learning. This paper proposes a verifiable decentralized FL system for end-to-end integrity and authenticity of data and computation. It introduces a two-step proving and verification (2PV) method to address the conflict between confidentiality and transparency. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re working on a team where everyone contributes their own information, but you want to make sure that nobody cheats or changes each other’s work. That’s kind of like what this paper is about. It proposes a way to verify that all the data and computations are honest and correct, without actually seeing any of the sensitive information. This is important because it helps keep everyone on the same page and makes sure that no one can manipulate the results. |
Keywords
* Artificial intelligence * Federated learning
