Home
Scholarly Works
CryptoEyes: Privacy Preserving Classification over...
Conference

CryptoEyes: Privacy Preserving Classification over Encrypted Images

Abstract

With the concern of privacy, a user usually encrypts the images before they were uploaded to the cloud service providers. Classification over encrypted images is essential for the service providers to collect coarse-grained statistical information about the images, therefore offering better services without sacrificing users’ privacy. In this paper, we propose CryptoEyes to address the challenges of privacy-preserving classification over encrypted images. We present a two-stream convolutional network architecture for classification over encrypted images to capture the contour of encrypted images, therefore significantly boosting the classification accuracy. By sharing a secret sequence between the service provider and the image owner, CryptoEyes allows the service provider to obtain category information of encrypted images while preventing the unauthorized users from learning it. We implemented and evaluated CryptoEyes on popular datasets and the experimental results demonstrate the superiority of CryptoEyes over existing state of the arts in terms of classification accuracy over encrypted images and better privacy preservation performance.

Authors

He W; Li S; Wang W; Wei M; Qiu B

Volume

00

Pagination

pp. 1-10

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Publication Date

May 13, 2021

DOI

10.1109/infocom42981.2021.9488738

Name of conference

IEEE INFOCOM 2021 - IEEE Conference on Computer Communications
View published work (Non-McMaster Users)

Contact the Experts team