Towards privacy-preserving split learning: Destabilizing adversarial inference and reconstruction attacks in the cloud
Internet of Things · 2025-05 · 31 · 101558
DOI: 10.1016/j.iot.2025.101558 ↗Kurz gefasst
Fachartikel in der Zeitschrift Internet of Things, 2025-05. Verfasst von Griffin Higgins und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 53 Literaturangaben.
Abstract (Originalsprache)
This work aims to provide both privacy and utility within a split learning framework while considering both forward attribute inference and backward reconstruction attacks. To address this, a novel approach has been proposed, which makes use of class activation maps and autoencoders as a plug-in strategy aiming to increase the user's privacy and destabilize an adversary. The proposed approach is compared with a dimensionality-reduction-based plug-in strategy, which makes use of principal component analysis to transform the feature map onto a lower-dimensional feature space. Our work shows that our proposed autoencoder-based approach is preferred as it can provide protection at an earlier split position over the tested architectures in our setting, and, hence, better utility for resource-constrained devices in edge-cloud collaborative inference (EC) systems.
Zitieren
APA
Higgins, G., Razavi-Far, R., Zhang, X., David, A., Ghorbani, A., & Ge, T. (2025). Towards privacy-preserving split learning: Destabilizing adversarial inference and reconstruction attacks in the cloud. Internet of Things, 31, 101558. https://doi.org/10.1016/j.iot.2025.101558
Vancouver
Higgins G, Razavi-Far R, Zhang X, David A, Ghorbani A, Ge T. Towards privacy-preserving split learning: Destabilizing adversarial inference and reconstruction attacks in the cloud. Internet of Things. 2025;31:101558. doi:10.1016/j.iot.2025.101558
BibTeX
@article{Higgins2025,
author = {Higgins, Griffin and Razavi-Far, Roozbeh and Zhang, Xichen and David, Amir and Ghorbani, Ali and Ge, Tongyu},
title = {Towards privacy-preserving split learning: Destabilizing adversarial inference and reconstruction attacks in the cloud},
journal = {Internet of Things},
year = {2025},
volume = {31},
pages = {101558},
doi = {10.1016/j.iot.2025.101558}
}
EUVIMED