Publisher: College of Information Science and Technology  

Date: October 21, 2024  

Professor Xiang Shijun's research team recently published a significant paper titled Image Semantic Steganography: A Way to Hide Information in Semantic Communication in the prestigious journal IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT). This journal is recognized as a leading publication in the fields of video and image technology, boasting a latest impact factor of 8.4.

 Overview of the Research

The paper introduces a novel approach to information hiding that leverages artificial intelligence, particularly by using Generating Adversarial Networks (GANs) in the context of semantic communication (SC). 

Key Contributions:

- Emerging Paradigm: Semantic communication transmits only the task-related semantic features, improving communication speed and efficiency. However, traditional methods in steganography face challenges in retaining the capability to accurately extract messages after semantic communication.

- Framework Development: The proposed framework, Image Semantic Steganography, embeds messages directly into semantic features. This approach ensures the successful extraction of messages while accounting for both pixel-level and semantic-level distortions, which enhances overall security.

- Experimental Validation: The research demonstrates that the framework achieves successful message extraction and behavioral covertness, maintaining the effectiveness of semantic communication without any detrimental impact.

 Team and Support

The paper's first author is Huo Yanhao, a doctoral student specializing in cybersecurity. Professor Xiang Shijun, who serves as the corresponding author, is a faculty member in the Department of Electronic Engineering, overseeing master's and doctoral students in Information and Communication Engineering and Cyberspace Security. 

The study received funding from several prestigious programs, including the National Key Research and Development Program, the National Natural Science Foundation of China General Project, and the Guangdong Provincial Natural Science Foundation General Project.

For further reading, the full paper can be accessed [here]

(https://xplorestaging.ieee.org/document/10711846).