BibTex format
@article{Muñoz-González:2019,
author = {Muñoz-González, L and Co, KT and Lupu, EC},
title = {Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging},
url = {http://arxiv.org/abs/1909.05125v1},
year = {2019}
}
Publications
Citation
RIS format (EndNote, RefMan)
TY - JOUR
AB - Federated learning enables training collaborative machine learning models atscale with many participants whilst preserving the privacy of their datasets.Standard federated learning techniques are vulnerable to Byzantine failures,biased local datasets, and poisoning attacks. In this paper we introduceAdaptive Federated Averaging, a novel algorithm for robust federated learningthat is designed to detect failures, attacks, and bad updates provided byparticipants in a collaborative model. We propose a Hidden Markov Model tomodel and learn the quality of model updates provided by each participantduring training. In contrast to existing robust federated learning schemes, wepropose a robust aggregation rule that detects and discards bad or maliciouslocal model updates at each training iteration. This includes a mechanism thatblocks unwanted participants, which also increases the computational andcommunication efficiency. Our experimental evaluation on 4 real datasets showthat our algorithm is significantly more robust to faulty, noisy and maliciousparticipants, whilst being computationally more efficient than otherstate-of-the-art robust federated learning methods such as Multi-KRUM andcoordinate-wise median.
AU - Muñoz-González,L
AU - Co,KT
AU - Lupu,EC
PY - 2019///
TI - Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
UR - http://arxiv.org/abs/1909.05125v1
ER -