Split Learning with Differential Privacy for Integrated Terrestrial and Non-Terrestrial Networks

Integrated terrestrial and non-terrestrial networks (TNTNs) have become a promising architecture for enabling ubiquitous connectivity. Smart remote sensing is one of the typical applications of TNTNs that collects and analyzes various dimensions of remote sensing data by deploying Internet of Things (IoT) sensors and edge computing in terrestrial, space, aerial, and underwater networks. To improve the analysis accuracy of remote sensing data, the owners of different networks should conduct collaborative learning on different dimensions of data, while data and label privacy should be jointly considered. However, the existing collaborative learning paradigms have difficulty in meeting this demand. In this article, we propose a paradigm of split learning (SL), where the data owner and the label owner train different parts of the deep learning model and only exchange the intermediate data (i.e., smashed data and cut layer gradients). We explore the potential privacy attacks that recover the raw data and label information based on the intermediate data and propose the differential privacy (DP) based defense mechanisms that inject randomly generated Laplace noise into the intermediate data to disturb the attack performance. We also conduct a simulation study based on a real-world satellite remote sensing dataset to prove that the SL paradigm with defense mechanisms can effectively balance the performance of the collaborative model training and the protection of the data and label privacy. Finally, we discuss the main challenges and potential research directions of the privacy-preserving SL paradigm for smart remote sensing over TNTNs.

Introduction

With the vast improvement in communication network technologies, smart remote sensing over integrated terrestrial and non-terrestrial networks (TNTNs) has attracted lots of interest and applications in the past decades. In the meantime, the emergence of big data applications and rapid growth in the number of wireless terminals are pushing the infrastructures of traditional ground communications to their limits. In order to extend the current network capabilities and resources, TNTN has been envisioned as an innovative paradigm to incorporate terrestrial networks and non-terrestrial networks including space, aerial, and underwater networks [1]. By deploying advanced sensing devices and utilizing multi-sensor mobile devices, TNTN can provide smart remote sensing to measure electromagnetic fields, capture images and videos, and collect various types of sensing data. The cooperation of terrestrial networks and non-terrestrial networks in collecting, transmitting, storing, and analyzing remote sensing data supports more elaborated and holistic data analysis for various applications, such as natural resource exploration, environment monitoring, and disaster tracking [2].