Summary of Fake or Compromised? Making Sense Of Malicious Clients in Federated Learning, by Hamid Mozaffari et al.
Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
by Hamid Mozaffari, Sunav Choudhary, Amir Houmansadr
First submitted to arxiv on: 10 Mar 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 This paper aims to clarify the confusion in federated learning (FL) security against poisoning attacks by presenting a comprehensive analysis of various poisoning attacks and defensive aggregation rules (AGRs). The authors propose a hybrid adversary model that lies between existing models, compromising a few clients and generating synthetic data for stronger attacks. The study connects different adversary models under a common framework, providing practitioners and researchers with a clear understanding of FL threats and identifying areas for further research. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Federated learning is a way to train artificial intelligence models without sharing private data. Some people want to ruin this by adding fake information to the training process. The problem is that there are many ways to do this, and it’s hard to know which ones to worry about. This paper tries to solve this problem by looking at all the different ways hackers might attack federated learning systems and how they can be stopped. It also proposes a new way of thinking about these attacks, which could help make FL safer. |
Keywords
* Artificial intelligence * Federated learning * Synthetic data
