Loading Now

Summary of Recovering Labels From Local Updates in Federated Learning, by Huancheng Chen and Haris Vikalo


Recovering Labels from Local Updates in Federated Learning

by Huancheng Chen, Haris Vikalo

First submitted to arxiv on: 2 May 2024

Categories

  • Main: Machine Learning (cs.LG)
  • Secondary: Cryptography and Security (cs.CR)

     Abstract of paper      PDF of paper


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 novel label recovery scheme called Recovering Labels from Local Updates (RLU) to address gradient inversion (GI) attacks in federated learning (FL). RLU achieves near-perfect accuracy when attacking untrained models and high performance even in realistic settings where clients run multiple local epochs, train on heterogeneous data, and use various optimizers. The method estimates labels by solving a least-square problem analyzing the correlation between label and update of the output layer. Experimental results on several datasets, architectures, and data heterogeneity scenarios demonstrate that RLU outperforms existing baselines in terms of PSNR and LPIPS for reconstructed images.
Low GrooveSquid.com (original content) Low Difficulty Summary
This paper helps keep our personal data safe by developing a new way to recover labels from model updates in federated learning. This is important because some hackers might try to figure out what we’re doing based on the tiny pieces of information they get from us. The team came up with a clever method that can do this really well, even when things are complex and different parts are working together in strange ways. They tested it on many different cases and showed that it’s way better than other methods at keeping our data safe.

Keywords

» Artificial intelligence  » Federated learning