Abstract
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.
Highlights
IntroductionSatellite images of earth are generated by imaging satellites, which may be operated by governments or enterprises
Visual observation is appropriate in certain situations, but it does not indicate the amount of information hidden
Various security threats and corresponding defensive privacy-preserving deep learning (PPDL) techniques have attracted much attention in both the research community and in global interests such as military operations and business. With such an increased interest in processing satellite image data, there comes a great demand for preserving privacy when using public deep learning (DL) technique for processing satellite images
Summary
Satellite images of earth are generated by imaging satellites, which may be operated by governments or enterprises These images are captured through remote sensing (RS). The main concern is to detect them throughout the provided images, regardless of their actual location therein Another essential characteristic of CNN is found in how it acquires conceptual characteristics as data spread into the deeper layers. The edge could be identified throughout the first layer of the image classification, and simple features could be identified in the second layer before the top-level features such as objects are identified in the layers [13] In this way, CNN addresses the over-fitting issue wherein the neuron within a layer will be connected to the previous layer with a small region rather than all neurons, as usually happens in fully-connected neural networks
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call