A Huber Loss Minimization Approach to Byzantine Robust Federated Learning

Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhao, Puning, Yu, Fei, Wan, Zhiguo
Format: Conference Proceeding
Language:English
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically distributed (i.i.d) assumption, our approach has several advantages compared to existing methods. Firstly, it has optimal dependence on epsilon, which stands for the ratio of attacked clients. Secondly, our approach does not need precise knowledge of epsilon. Thirdly, it allows different clients to have unequal data sizes. We then broaden our analysis to include non-i.i.d data, such that clients have slightly different distributions.
ISSN:2159-5399
2374-3468
DOI:10.1609/aaai.v38i19.30181