CSA-SHE: Channel and Spatial Attention With Selective Homomorphic Encryption for Privacy-Preserving Semantic Communication in Space–Air–Ground Integrated Networks

Abstract

Space-Air-Ground Integrated Networks (SAGINs) represent a revolutionary paradigm to attain seamless and ubiquitous connectivity by incorporating space-based, aerial, and ground communication systems. Semantic communication in SAGINs is a promise to improve transmission efficiency by conveying only the meaning of data rather than raw bits. However, there are risks associated with transmitting semantic-rich data over insecure channels. Sensitive information leakage poses security challenges for node-to-node semantic communications. This paper addresses this problem when face images are transmitted over wireless channels in the presence of an illegitimate receiver. The paper proposes a new semantic communication approach that ensures privacy by applying selective homomorphic encryption (SHE) for protection and deprotection. The scheme represents a cutting-edge direction that blends privacy-preserving computation with deep visual understanding. The proposed system leverages the potential of channel and spatial attention (CSA) mechanisms for communicating nodes’ architectures and optimization. It exploits the selective homomorphic encryption for facial landmarks-aware encryption, where feature-level adaptivity is employed to ensure semantic information is securely conveyed from the high-altitude platform station (HAPS) node to the legitimate receiver on the ground. Simulation findings indicate the proposed scheme’s efficiency in preventing ground illegitimate receivers from reconstructing valuable face regions of interest (ROIs) while ensuring high-fidelity legitimate full image reconstruction. Furthermore, the proposed system reveals that applying attention mechanisms and encrypting only semantic features of interest can lead to lower processing and communication costs.