Ahsen Tahir
Can Federated Models Be Rectified Through Learning Negative Gradients?
Tahir, Ahsen; Tan, Zhiyuan; Babaagba, Kehinde O.
Authors
Dr Thomas Tan Z.Tan@napier.ac.uk
Associate Professor
Dr Kehinde Babaagba K.Babaagba@napier.ac.uk
Lecturer
Abstract
Federated Learning (FL) is a method to train machine learning (ML) models in a decentralised manner, while preserving the privacy of data from multiple clients. However, FL is vulnerable to malicious attacks, such as poisoning attacks, and is challenged by the GDPR’s “right to be forgotten”. This paper introduces a negative gradient-based machine learning technique to address these issues. Experiments on the MNIST dataset show that subtracting local model parameters can remove the influence of the respective training data on the global model and consequently “unlearn” the model in the FL paradigm. Although the performance of the resulting global model decreases, the proposed technique maintains the validation accuracy of the model above 90%. This impact on performance is acceptable for an FL model. It is important to note that the experimental work carried out demonstrates that in application areas where data deletion in ML is a necessity, this approach represents a significant advancement in the development of secure and robust FL systems.
Citation
Tahir, A., Tan, Z., & Babaagba, K. O. Can Federated Models Be Rectified Through Learning Negative Gradients?. Presented at 13th EAI International Conference, BDTA 2023, Edinburgh
Presentation Conference Type | Conference Paper (Published) |
---|---|
Conference Name | 13th EAI International Conference, BDTA 2023 |
Online Publication Date | Jan 31, 2024 |
Publication Date | 2024 |
Deposit Date | Feb 2, 2024 |
Publicly Available Date | Feb 1, 2025 |
Publisher | Springer |
Pages | 18-32 |
Series Title | Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST) |
Series Number | 555 |
Series ISSN | 1867-8211 |
Book Title | Big Data Technologies and Applications |
ISBN | 978-3-031-52264-2 |
DOI | https://doi.org/10.1007/978-3-031-52265-9_2 |
Keywords | Federated Learning, Machine Unlearning, Negative Gradients, Model Rectification |
Public URL | http://researchrepository.napier.ac.uk/Output/3500047 |
Files
This file is under embargo until Feb 1, 2025 due to copyright reasons.
Contact repository@napier.ac.uk to request a copy for personal use.
Related Outputs
Big Data Technologies and Applications: 13th EAI International Conference, BDTA 2023, Edinburgh, UK, August 23-24, 2023, Proceedings
(2024)
Presentation / Conference Contribution
Machine Un-learning: An Overview of Techniques, Applications, and Future Directions
(2023)
Journal Article
You might also like
Nowhere Metamorphic Malware Can Hide - A Biological Evolution Inspired Detection Scheme
(2019)
Presentation / Conference Contribution
A Study on the Effect of Feature Selection on Malware Analysis using Machine Learning
(2019)
Presentation / Conference Contribution
A Generative Neural Network for Enhancing Android Metamorphic Malware Detection based on Behaviour Profiling
(2022)
Presentation / Conference Contribution
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search