Open Access

ARTICLE

Semantic Secure Communication Based on the Joint Source-Channel Coding

Yifeng Lin^1,2,#, Yuer Yang^1,2,3,#, Jianxiang Xie⁴, Tong Ji⁵, Peiya Li^2,*

1 Department of Computer Science, The University of Hong Kong, Hong Kong, 999077, China
2 College of Cyber Security, Jinan University, Guangzhou, 511436, China
3 School of Economics, Jinan University, Guangzhou, 510632, China
4 School of Computer Science and Engineering, The University of New South Wales, Kensington, Sydney, NSW 2052, Australia
5 College of Information Science and Technology, Jinan University, Guangzhou, 511436, China

* Corresponding Author: Peiya Li. Email:
# These authors contributed equally to this work

(This article belongs to the Special Issue: Privacy in the Digital Age: AI-Driven Image Encryption for Secure Data Transmission)

Computers, Materials & Continua 2025, 84(2), 2865-2882. https://doi.org/10.32604/cmc.2025.065362

Received 10 March 2025; Accepted 09 May 2025; Issue published 03 July 2025

Abstract

Semantic secure communication is an emerging field that combines the principles of source-channel coding with the need for secure data transmission. It is of great significance in modern communications to protect the confidentiality and privacy of sensitive information and prevent information leaks and malicious attacks. This paper presents a novel approach to semantic secure communication through the utilization of joint source-channel coding, which is based on the design of an automated joint source-channel coding algorithm and an encryption and decryption algorithm based on semantic security. The traditional and state-of-the-art joint source-channel coding algorithms are selected as two baselines for different comparison purposes. Experimental results demonstrate that our proposed algorithm outperforms the first baseline algorithm, the traditional source-channel coding, by 61.21% in efficiency under identical channel conditions (). In security, our proposed method can resist 2 more types of attacks compared to the two baselines, exhibiting nearly no increases in time consumption and error rate compared to the state-of-the-art joint source-channel coding algorithm while the secure semantic communication is supported.

---

Keywords

---