Anglia Ruskin Research Online (ARRO)
Browse

Federated Learning-based Personalized Recommendation Systems: An Overview on Security and Privacy Challenges

Download (721.45 kB)
journal contribution
posted on 2023-10-31, 11:50 authored by Danish Javeed, Muhammad Shahid Saeed, Prabhat Kumar, Alireza Jolfaei, Shareeful Islam, AKM Najmul Islam

The recent advancement in next-generation Consumer Electronics (CE) has  created the problems of information overload and information loss. The  significance of Personalized Recommendation Systems (PRS) to efficiently  and effectively extract useful user information is seen as an ideal  solution to provide users with personalized content and services and  therefore is used in different application domains including healthcare,  e-commerce, social media, etc. Security and privacy are the two major  challenges of the existing PRS for next-gen CE data. Federated learning  (FL) has the potential to elevate the aforementioned challenges by  sharing local recommender parameters while keeping all the training data  on the device and therefore is seen as a promising technique to enhance  security and privacy in PRS for the next-gen CE data. In this survey,  we have first discussed the enhancement of the existing CE technologies,  a holistic review of security and privacy challenges in current PRS,  and the advantage of FL-based PRS for next-gen CE. Finally, we list a  few open issues and challenges that can guide researchers and  practitioners to further drive research in this promising area. 

History

Refereed

  • Yes

Page range

1-1

Publication title

IEEE Transactions on Consumer Electronics

ISSN

0098-3063

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

File version

  • Accepted version

Affiliated with

  • School of Computing and Information Science Outputs

Note

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works