Controlled Privacy Leakage Propagation Throughout Overlapping Grouped Learning
IEEE Journal on Selected Areas in Information Theory · 2024 · 5 · 442-463
DOI: 10.1109/jsait.2024.3416089 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Information Theory, 2024. Verfasst von Shahrzad Kiani und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: Discovery Research Grant from the Natural Sciences and Engineering Research Council of Canada, NSERC Alexander Graham Bell Canada Graduate Scholarship-Doctoral, DiDi Graduate Award.
Abstract (Originalsprache)
Federated Learning (FL) is the standard protocol for collaborative learning. In FL, multiple workers jointly train a shared model. They exchange model updates calculated on their data, while keeping the raw data itself local. Since workers naturally form groups based on common interests and privacy policies, we are motivated to extend standard FL to reflect a setting with multiple, potentially overlapping groups. In this setup where workers can belong and contribute to more than one group at a time, complexities arise in understanding privacy leakage and in adhering to privacy policies. To address the challenges, we propose differential private overlapping grouped learning (DP-OGL), a novel method to implement privacy guarantees within overlapping groups. Under the honest-but-curious threat model, we derive novel privacy guarantees between arbitrary pairs of workers. These privacy guarantees describe and quantify two key effects of privacy leakage in DP-OGL: propagation delay, i.e., the fact that information from one group will leak to other groups only with temporal offset through the common workers and information degradation, i.e., the fact that noise addition over model updates limits information leakage between workers. Our experiments show that applying DP-OGL enhances utility while maintaining strong privacy compared to standard FL setups.
Förderung
- Discovery Research Grant from the Natural Sciences and Engineering Research Council of Canada
- NSERC Alexander Graham Bell Canada Graduate Scholarship-Doctoral
- DiDi Graduate Award
Zitieren
APA
Kiani, S., Boenisch, F., & Draper, S. C. (2024). Controlled Privacy Leakage Propagation Throughout Overlapping Grouped Learning. IEEE Journal on Selected Areas in Information Theory, 5, 442-463. https://doi.org/10.1109/jsait.2024.3416089
Vancouver
Kiani S, Boenisch F, Draper SC. Controlled Privacy Leakage Propagation Throughout Overlapping Grouped Learning. IEEE Journal on Selected Areas in Information Theory. 2024;5:442-463. doi:10.1109/jsait.2024.3416089
BibTeX
@article{Kiani2024,
author = {Kiani, Shahrzad and Boenisch, Franziska and Draper, Stark C.},
title = {Controlled Privacy Leakage Propagation Throughout Overlapping Grouped Learning},
journal = {IEEE Journal on Selected Areas in Information Theory},
year = {2024},
volume = {5},
pages = {442--463},
doi = {10.1109/jsait.2024.3416089}
}
EUVIMED