Cross-Layer Encrypted Semantic Communication Framework for Panoramic Video Transmission

TL;DR

Compared to traditional cross-layer transmission schemes, the proposed CLESC framework can reduce bandwidth consumption by 85% while showing significant advantages under low signal-to-noise ratio (SNR) conditions.

Abstract

In this paper, we propose a cross-layer encrypted semantic communication (CLESC) framework for panoramic video transmission, incorporating feature extraction, encoding, encryption, cyclic redundancy check (CRC), and retransmission processes to achieve compatibility between semantic communication and traditional communication systems. Additionally, we propose an adaptive cross-layer transmission mechanism that dynamically adjusts CRC, channel coding, and retransmission schemes based on the importance of semantic information. This ensures that important information is prioritized under poor transmission conditions. To verify the aforementioned framework, we also design an end-to-end adaptive panoramic video semantic transmission (APVST) network that leverages a deep joint source-channel coding (Deep JSCC) structure and attention mechanism, integrated with a latitude adaptive module that facilitates adaptive semantic feature extraction and variable-length encoding of panoramic videos. The proposed CLESC is also applicable to the transmission of other modal data. Simulation results demonstrate that the proposed CLESC effectively achieves compatibility and adaptation between semantic communication and traditional communication systems, improving both transmission efficiency and channel adaptability. Compared to traditional cross-layer transmission schemes, the CLESC framework can reduce bandwidth consumption by 85% while showing significant advantages under low signal-to-noise ratio (SNR) conditions.

Figures (9)

• Figure 1: The schemes of semantic communication and traditional mobile communication framework compatibility and adaptation.
• Figure 2: The framework of cross-layer encrypted semantic communication framework.
• Figure 3: Network structures of APVST. $k\times k$ Conv is a convolution with $k\times k$ filters, and the output channels of convolution are given on horizontal line. $\uparrow2$ and $\downarrow2$ indicate upsampling and downsampling with a stride of 2. GDN denotes the Generalised Divisive Normalization in density_modeling_images, IGDN denotes the inverse operation of GDN.
• Figure 4: Detailed structures of (a) WA Module, and (b) Latitude Adaptive Module.
• Figure 5: WS-PSNR performance vs. (a) CBR at SNR=5dB, (b) SNR at CBR=0.04, and (c) average retransmission times at SNR=5dB and CBR=0.04 with BPSK modulation.