Breakwater: Securing Federated Learning from Malicious Model Poisoning via Self-Debiasing

Yeawon You, Jin Yi Yoon, Hyung June Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deep learning models deployed on edge devices leverage locally collected data to extract intelligence, mitigating privacy concerns associated with external data sharing. Edge federated learning, an on-device learning paradigm, has emerged as a promising solution, allowing edge nodes to train models locally and share only the trained weights, preserving data privacy. However, it also poses critical challenges of network burden and potential model poisoning. We introduce a self-debiasing security framework Breakwater for multi-hop edge federated learning. We incorporate on-device malicious weight discriminator at each participant, enhancing security and robustness of the federated learning process. The framework strategically balances the benefits of participating nodes with timely defenses against potential malicious clients. Based on the discriminator, we further embed a self-debiasing mechanism that can determine whether to retain or discard the weight propagation from its child nodes. Our Breakwater framework identifies and filters out harmful weights, ensuring the integrity of the global model. Our work contributes to the ongoing discourse on federated learning security, presenting a solution that maintains efficiency while robustly defending against model poisoning threats. We demonstrate its efficacy in enhancing the reliability of the multi-hop edge federated learning process with recovery of up to 69 % in accuracy under attack, offering a path toward secure and cooperative distributed learning environments.

Original languageEnglish
Title of host publicationICC 2024 - IEEE International Conference on Communications
EditorsMatthew Valenti, David Reed, Melissa Torres
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3956-3961
Number of pages6
ISBN (Electronic)9781728190549
DOIs
StatePublished - 2024
Event59th Annual IEEE International Conference on Communications, ICC 2024 - Denver, United States
Duration: 9 Jun 202413 Jun 2024

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Conference

Conference59th Annual IEEE International Conference on Communications, ICC 2024
Country/TerritoryUnited States
CityDenver
Period9/06/2413/06/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Fingerprint

Dive into the research topics of 'Breakwater: Securing Federated Learning from Malicious Model Poisoning via Self-Debiasing'. Together they form a unique fingerprint.

Cite this