aalto1 untyped-item.component.html

Robust Aggregation Technique Against Poisoning Attacks in Multi-Stage Federated Learning Applications

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

7

Series

2024 IEEE 21st Consumer Communications and Networking Conference, CCNC 2024, pp. 956-962, Proceedings - IEEE Consumer Communications and Networking Conference, CCNC

Abstract

Federated Learning (FL) is a distributed Machine Learning (ML) technique that allows model training without sharing data. FL is vulnerable to poisoning attacks where an adversary manipulates the learning process by providing false information to the federation. Ensuring security in FL is vital before using FL in real applications, as the consequences can be adverse. Multi-stage FL is a novel variant of FL that performs intermediate model aggregations, thereby reducing the traffic toward the FL central server. The existing robust aggregation techniques are insufficient in multi-stage FL systems. This paper proposes a novel robust aggregation algorithm against poisoning attacks in a three-layer multi-stage FL system that consists of device, edge, and cloud layers. We evaluate the proposed robust algorithm considering an Augmented Reality (AR) application with different poisoner placements and attack strategies. The evaluation results show that the proposed algorithm can effectively defend against poisoning attacks in three-layer multi-stage FL systems.

Description

Publisher Copyright: © 2024 IEEE.

Other note

Citation

Siriwardhana, Y, Porambage, P, Liyanage, M, Marchal, S & Ylianttila, M 2024, Robust Aggregation Technique Against Poisoning Attacks in Multi-Stage Federated Learning Applications. in 2024 IEEE 21st Consumer Communications and Networking Conference, CCNC 2024. Proceedings - IEEE Consumer Communications and Networking Conference, CCNC, IEEE, pp. 956-962, IEEE Consumer Communications and Networking Conference, Las Vegas, Nevada, United States, 06/01/2024. https://doi.org/10.1109/CCNC51664.2024.10454789

Endorsement

Review

Supplemented By

Referenced By