Summary of Brave: Byzantine-resilient and Privacy-preserving Peer-to-peer Federated Learning, by Zhangchen Xu et al.
Brave: Byzantine-Resilient and Privacy-Preserving Peer-to-Peer Federated Learning
by Zhangchen Xu, Fengqing Jiang, Luyao Niu, Jinyuan Jia, Radha Poovendran
First submitted to arxiv on: 10 Jan 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 This paper proposes a federated learning (FL) protocol called Brave, which enables multiple participants to train a global machine learning model without sharing their private training data. Building on peer-to-peer (P2P) FL, Brave ensures Byzantine resilience and preserves privacy in the presence of both honest-but-curious and Byzantine adversaries. The protocol’s core idea is to ensure that all benign participants converge to an identical model that deviates from a global model trained without Byzantine adversaries by a bounded distance. To evaluate Brave, the authors conduct experiments on P2P FL for image classification tasks using benchmark datasets CIFAR10 and MNIST, demonstrating comparable classification accuracy to a global model trained in the absence of any adversary. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning lets many people work together on a big project without sharing their secrets. This is good because it keeps things private! But sometimes bad guys might try to ruin the project by sending fake information or trying to figure out what others are working on. Brave is a new way to do federated learning that makes sure these bad guys can’t succeed. It’s like having a special shield that keeps everyone’s secrets safe and helps them all work together to create something great! |
Keywords
* Artificial intelligence * Classification * Federated learning * Image classification * Machine learning
