Research on robustness of federated learning based on pruning optimization

Lei Zhao; Yitong Chen

doi:10.1117/12.3049006

12 November 2024 Research on robustness of federated learning based on pruning optimization

Lei Zhao, Yitong Chen

Author Affiliations +

Proceedings Volume 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) ; 133952G (2024) https://doi.org/10.1117/12.3049006
Event: International Conference on Optics, Electronics, and Communication Engineering, 2024, Wuhan, China

Abstract

Federated learning has more flexible data ownership participants, therefore its data (sample feature vector or label) is more likely to be changed, and it is more vulnerable to data poisoning by malicious users, resulting in the final global model not getting the expected effect. This paper focuses on this data poisoning defense problem and applies the traditional centralized machine learning pruning optimization method to each client of federated learning. Each client needs to execute before each global iteration. Pruning optimization algorithm to remove abnormal data. The experimental results indicate that when the discrepancy between abnormal and normal samples is significant, the pruning optimization algorithm effectively eliminates the outliers, thereby minimizing their impact on the final federated learning model.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Lei Zhao and Yitong Chen "Research on robustness of federated learning based on pruning optimization", Proc. SPIE 13395, International Conference on Optics, Electronics, and Communication Engineering (OECE 2024) , 133952G (12 November 2024); https://doi.org/10.1117/12.3049006

Access the abstract

PROCEEDINGS
7 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Data modeling

Mathematical optimization

Education and training

Statistical modeling

Adversarial training

Defense and security

Show All Keywords

RELATED CONTENT

Predicting effective arguments based on hybrid language model
Proceedings of SPIE (May 23 2023)

Optimization of YOLOv8 model based on pruning
Proceedings of SPIE (November 08 2024)

Railway wagon number recognition method based on combined GWO-SVM
Proceedings of SPIE (June 08 2023)

Coupon recommendation system based on machine learning and simulated annealing...
Proceedings of SPIE (June 01 2023)

Research on XSS adversarial attack model based on reinforcement learning
Proceedings of SPIE (October 20 2023)

Enhancing adversarial robustness in image classification models through frequency mutual...
Proceedings of SPIE (August 23 2024)

A transfer model for evaluating text classification models based on...
Proceedings of SPIE (April 08 2024)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years