Open Access iconOpen Access

ARTICLE

crossmark

A General Linguistic Steganalysis Framework Using Multi-Task Learning

Lingyun Xiang1,*, Rong Wang1, Yuhang Liu1, Yangfan Liu1, Lina Tan2,3

1 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
2 School of Computer Science and Electronic Engineering, University of Essex, Colchester, CO4 3SQ, UK
3 School of Computer Science, Hunan University of Technology and Business, Changsha, 410205, China

* Corresponding Author: Lingyun Xiang. Email: email

Computer Systems Science and Engineering 2023, 46(2), 2383-2399. https://doi.org/10.32604/csse.2023.037067

Abstract

Prevailing linguistic steganalysis approaches focus on learning sensitive features to distinguish a particular category of steganographic texts from non-steganographic texts, by performing binary classification. While it remains an unsolved problem and poses a significant threat to the security of cyberspace when various categories of non-steganographic or steganographic texts coexist. In this paper, we propose a general linguistic steganalysis framework named LS-MTL, which introduces the idea of multi-task learning to deal with the classification of various categories of steganographic and non-steganographic texts. LS-MTL captures sensitive linguistic features from multiple related linguistic steganalysis tasks and can concurrently handle diverse tasks with a constructed model. In the proposed framework, convolutional neural networks (CNNs) are utilized as private base models to extract sensitive features for each steganalysis task. Besides, a shared CNN is built to capture potential interaction information and share linguistic features among all tasks. Finally, LS-MTL incorporates the private and shared sensitive features to identify the detected text as steganographic or non-steganographic. Experimental results demonstrate that the proposed framework LS-MTL outperforms the baseline in the multi-category linguistic steganalysis task, while average Acc, Pre, and Rec are increased by 0.5%, 1.4%, and 0.4%, respectively. More ablation experimental results show that LS-MTL with the shared module has robust generalization capability and achieves good detection performance even in the case of spare data.

Keywords

Linguistic steganalysis; multi-task learning; convolutional neural network (CNN); feature extraction; detection performance

Cite This Article

APA Style
Xiang, L., Wang, R., Liu, Y., Liu, Y., Tan, L. (2023). A General Linguistic Steganalysis Framework Using Multi-Task Learning. Computer Systems Science and Engineering, 46(2), 2383–2399. https://doi.org/10.32604/csse.2023.037067
Vancouver Style
Xiang L, Wang R, Liu Y, Liu Y, Tan L. A General Linguistic Steganalysis Framework Using Multi-Task Learning. Comput Syst Sci Eng. 2023;46(2):2383–2399. https://doi.org/10.32604/csse.2023.037067
IEEE Style
L. Xiang, R. Wang, Y. Liu, Y. Liu, and L. Tan, “A General Linguistic Steganalysis Framework Using Multi-Task Learning,” Comput. Syst. Sci. Eng., vol. 46, no. 2, pp. 2383–2399, 2023. https://doi.org/10.32604/csse.2023.037067



cc Copyright © 2023 The Author(s). Published by Tech Science Press.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 1067

    View

  • 949

    Download

  • 0

    Like

Share Link