Robust and Resilient Federated Learning for Securing Future Networks

Files in This Item:
 File SizeFormat
DownloadConf_EUCNC_2022_FL_Security_Submission.pdf263.9 kBAdobe PDF
Title: Robust and Resilient Federated Learning for Securing Future Networks
Authors: Siriwardhana, YushanPorambage, PawaniLiyanage, MadhusankaYlianttila, Mika
Permanent link: http://hdl.handle.net/10197/13091
Date: 10-Jun-2022
Online since: 2022-08-24T11:04:48Z
Abstract: Machine Learning (ML) and Artificial Intelligence (AI) techniques are widely adopted in the telecommunication industry, especially to automate beyond 5G networks. Federated Learning (FL) recently emerged as a distributed ML approach that enables localized model training to keep data decentralized to ensure data privacy. In this paper, we identify the applicabil- ity of FL for securing future networks and its limitations due to the vulnerability to poisoning attacks. First, we investigate the shortcomings of state-of-the-art security algorithms for FL and perform an attack to circumvent FoolsGold algorithm, which is known as one of the most promising defense techniques currently available. The attack is launched with the addition of intelligent noise at the poisonous model updates. Then we propose a more sophisticated defense strategy, a threshold-based clustering mechanism to complement FoolsGold. Moreover, we provide a comprehensive analysis of the impact of the attack scenario and the performance of the defense mechanism.
Funding Details: European Commission Horizon 2020
Type of material: Conference Publication
Publisher: IEEE
Start page: 351
End page: 356
Copyright (published version): 2022 IEEE
Keywords: Federated learningPoisoning attacksDefense mechanismLabel flipping
DOI: 10.1109/eucnc/6gsummit54941.2022.9815812
Language: en
Status of Item: Peer reviewed
Is part of: 2022 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Appears in Collections:Computer Science Research Collection

Show full item record

Page view(s)

106
Last Week
12
Last month
checked on Sep 26, 2022

Download(s)

13
checked on Sep 26, 2022

Google ScholarTM

Check

Altmetric


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.