Saved in:
Bibliographic Details
Main Authors: Sepehri, Yamin, Pad, Pedram, Frossard, Pascal, Dunbar, L. Andrea
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.05092
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916524450643968
author Sepehri, Yamin
Pad, Pedram
Frossard, Pascal
Dunbar, L. Andrea
author_facet Sepehri, Yamin
Pad, Pedram
Frossard, Pascal
Dunbar, L. Andrea
contents The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical images. In this work, we propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server that prevents sensitive content being transmitted to the cloud while retaining the desired information. The proposed privacy-preserving method uses adversarial early exits to suppress the sensitive content at the edge and transmits the task-relevant information to the cloud. This approach incorporates noise addition during the training phase to provide a differential privacy guarantee. We extensively test our method on different facial and medical datasets with diverse attributes using various deep learning architectures, showcasing its outstanding performance. We also demonstrate the effectiveness of privacy preservation through successful defenses against different white-box, deep and GAN-based reconstruction attacks. This approach is designed for resource-constrained edge devices, ensuring minimal memory usage and computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05092
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
Sepehri, Yamin
Pad, Pedram
Frossard, Pascal
Dunbar, L. Andrea
Computer Vision and Pattern Recognition
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
Image and Video Processing
I.2.10; I.2.6; I.2.11; K.4.1
The training phase of deep neural networks requires substantial resources and as such is often performed on cloud servers. However, this raises privacy concerns when the training dataset contains sensitive content, e.g., facial or medical images. In this work, we propose a method to perform the training phase of a deep learning model on both an edge device and a cloud server that prevents sensitive content being transmitted to the cloud while retaining the desired information. The proposed privacy-preserving method uses adversarial early exits to suppress the sensitive content at the edge and transmits the task-relevant information to the cloud. This approach incorporates noise addition during the training phase to provide a differential privacy guarantee. We extensively test our method on different facial and medical datasets with diverse attributes using various deep learning architectures, showcasing its outstanding performance. We also demonstrate the effectiveness of privacy preservation through successful defenses against different white-box, deep and GAN-based reconstruction attacks. This approach is designed for resource-constrained edge devices, ensuring minimal memory usage and computational overhead.
title PriPHiT: Privacy-Preserving Hierarchical Training of Deep Neural Networks
topic Computer Vision and Pattern Recognition
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Machine Learning
Image and Video Processing
I.2.10; I.2.6; I.2.11; K.4.1
url https://arxiv.org/abs/2408.05092