Ieee federated Machine Learning White Paper
Download 0.56 Mb. View original pdf
|
e-Iraq estra.ar.en
| 16 IEEE SA such as biometric data, photos, and other personal information will infringe on user privacy and could potentially violate laws and regulations. Therefore, FML is a technical solution for improving model performance without compromising user privacy. Taking personalized recommendation services as an examplerecommendation systems are often used to manage users flight, meeting, and hotel booking information and provide recommendations based on users personal information such as contacts, message, calendar, location, sports/sleep data, app usage etc. In these cases, horizontal FML techniques can provide a more secure and trustworthy solution to help prevent leakage of sensitive personal data. Authorized licensed use limited to University of Malta. Downloaded on December 24,2022 at 11:03:39 UTC from IEEE Xplore. Restrictions apply. Copyright © 2021 IEEE. All rights reserved. 17 IEEE SA 4. REFERENCES The following list of sources either has been referenced within this paper or maybe useful for additional reading IEEE Std 3652.1-2020, IEEE Guide for Architectural Framework and Application of Federated Machine Learning, 2020. https://standards.ieee.org/standard/3652_1-2020.html [2] Jakub Konecný, H. Brendan McMahan, Daniel Ramage, and Peter Richtárik. a. Federated Optimization Distributed Machine Learning for On-Device Intelligence. CoRR abs (2016). Peter Kairouz, et al., Advances and Open Problems in Federated Learning, Foundations and Trends in Machine Learning Vol 4 Issue 1. http://dx.doi.org/10.1561/2200000083 . 2021. [4] Qiang Yang, Yang Liu, Yong Cheng, Yan Kang, Tianjian Chen, Han Yu. Federated Learning. ISBN 9781681736976, https://doi.org/10.2200/S00960ED2V01Y201910AIM043 . Morgan & Claypool Publishers, Dec 2019. H. Brendan McMahan, et al. Federated Learning of Deep Networks using Model Averaging. CoRR abs (2016). arXiv:1602.05629, 2016. Keith Bonawitz, et al. Practical Secure Aggregation for Privacy-Preserving Machine Learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS ’17). ACM, New York, NY, USA, 1175–1191. 2017. [7] Qiang Yang, Yu Zhang, Wenyuan Dai and Sinno Jilin Pan, Transfer Learning. ISBN 9781139061773. DOI: https://doi.org/10.1017/9781139061773 . Cambridge University Press. Jan. 2020. Authorized licensed use limited to University of Malta. Downloaded on December 24,2022 at 11:03:39 UTC from IEEE Xplore. Restrictions apply. |