An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification
Satellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also i...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/11/2221 |
id |
doaj-46de3b62d64c4c52bb1c6a97b765207d |
---|---|
record_format |
Article |
spelling |
doaj-46de3b62d64c4c52bb1c6a97b765207d2021-06-30T23:25:48ZengMDPI AGRemote Sensing2072-42922021-06-01132221222110.3390/rs13112221An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image ClassificationMunirah Alkhelaiwi0Wadii Boulila1Jawad Ahmad2Anis Koubaa3Maha Driss4College of Computer Science and Engineering, Taibah University, Medina 42353, Saudi ArabiaCollege of Computer Science and Engineering, Taibah University, Medina 42353, Saudi ArabiaSchool of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UKRobotics and Internet-of-Things Laboratory, Prince Sultan University, Riyadh 12435, Saudi ArabiaCollege of Computer Science and Engineering, Taibah University, Medina 42353, Saudi ArabiaSatellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also introduced various deep learning (DL) architectures to satellite imagery as a means of extracting useful information. However, this new approach comes with its own issues, including the fact that many users utilize ready-made cloud services (both public and private) in order to take advantage of built-in DL algorithms and thus avoid the complexity of developing their own DL architectures. However, this presents new challenges to protecting data against unauthorized access, mining and usage of sensitive information extracted from that data. Therefore, new privacy concerns regarding sensitive data in satellite images have arisen. This research proposes an efficient approach that takes advantage of privacy-preserving deep learning (PPDL)-based techniques to address privacy concerns regarding data from satellite images when applying public DL models. In this paper, we proposed a partially homomorphic encryption scheme (a Paillier scheme), which enables processing of confidential information without exposure of the underlying data. Our method achieves robust results when applied to a custom convolutional neural network (CNN) as well as to existing transfer learning methods. The proposed encryption scheme also allows for training CNN models on encrypted data directly, which requires lower computational overhead. Our experiments have been performed on a real-world dataset covering several regions across Saudi Arabia. The results demonstrate that our CNN-based models were able to retain data utility while maintaining data privacy. Security parameters such as correlation coefficient (−0.004), entropy (7.95), energy (0.01), contrast (10.57), number of pixel change rate (4.86), unified average change intensity (33.66), and more are in favor of our proposed encryption scheme. To the best of our knowledge, this research is also one of the first studies that applies PPDL-based techniques to satellite image data in any capacity.https://www.mdpi.com/2072-4292/13/11/2221privacy-preserving deep learningdeep learningremote sensingprivacy-preservationconvolutional neural networkhomomorphic encryption |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Munirah Alkhelaiwi Wadii Boulila Jawad Ahmad Anis Koubaa Maha Driss |
spellingShingle |
Munirah Alkhelaiwi Wadii Boulila Jawad Ahmad Anis Koubaa Maha Driss An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification Remote Sensing privacy-preserving deep learning deep learning remote sensing privacy-preservation convolutional neural network homomorphic encryption |
author_facet |
Munirah Alkhelaiwi Wadii Boulila Jawad Ahmad Anis Koubaa Maha Driss |
author_sort |
Munirah Alkhelaiwi |
title |
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification |
title_short |
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification |
title_full |
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification |
title_fullStr |
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification |
title_full_unstemmed |
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification |
title_sort |
efficient approach based on privacy-preserving deep learning for satellite image classification |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2021-06-01 |
description |
Satellite images have drawn increasing interest from a wide variety of users, including business and government, ever since their increased usage in important fields ranging from weather, forestry and agriculture to surface changes and biodiversity monitoring. Recent updates in the field have also introduced various deep learning (DL) architectures to satellite imagery as a means of extracting useful information. However, this new approach comes with its own issues, including the fact that many users utilize ready-made cloud services (both public and private) in order to take advantage of built-in DL algorithms and thus avoid the complexity of developing their own DL architectures. However, this presents new challenges to protecting data against unauthorized access, mining and usage of sensitive information extracted from that data. Therefore, new privacy concerns regarding sensitive data in satellite images have arisen. This research proposes an efficient approach that takes advantage of privacy-preserving deep learning (PPDL)-based techniques to address privacy concerns regarding data from satellite images when applying public DL models. In this paper, we proposed a partially homomorphic encryption scheme (a Paillier scheme), which enables processing of confidential information without exposure of the underlying data. Our method achieves robust results when applied to a custom convolutional neural network (CNN) as well as to existing transfer learning methods. The proposed encryption scheme also allows for training CNN models on encrypted data directly, which requires lower computational overhead. Our experiments have been performed on a real-world dataset covering several regions across Saudi Arabia. The results demonstrate that our CNN-based models were able to retain data utility while maintaining data privacy. Security parameters such as correlation coefficient (−0.004), entropy (7.95), energy (0.01), contrast (10.57), number of pixel change rate (4.86), unified average change intensity (33.66), and more are in favor of our proposed encryption scheme. To the best of our knowledge, this research is also one of the first studies that applies PPDL-based techniques to satellite image data in any capacity. |
topic |
privacy-preserving deep learning deep learning remote sensing privacy-preservation convolutional neural network homomorphic encryption |
url |
https://www.mdpi.com/2072-4292/13/11/2221 |
work_keys_str_mv |
AT munirahalkhelaiwi anefficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT wadiiboulila anefficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT jawadahmad anefficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT aniskoubaa anefficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT mahadriss anefficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT munirahalkhelaiwi efficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT wadiiboulila efficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT jawadahmad efficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT aniskoubaa efficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification AT mahadriss efficientapproachbasedonprivacypreservingdeeplearningforsatelliteimageclassification |
_version_ |
1721351320222302208 |