Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning
IEEE Transactions on Dependable and Secure Computing · 01.03.2023 · 20 (2) · 1476-1487
DOI: 10.1109/tdsc.2022.3156972 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, erschienen am 01.03.2023. Verfasst von Songbin Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Important Science and Technology Project of Hainan Province, Frontier Exploration Project Independently Deployed by Institute of Acoustics, Chinese Academy of Sciences.
Abstract (Originalsprache)
Covert communication channels can be easily constructed using text steganography based on social media. Offenders can easily utilize these channels to engage in various criminal activities, which brings great challenges in maintaining the security of cyberspace. Among the text information hiding methods, generative linguistic steganography poses the biggest threat to network security because it does not need the original carrier and has high embedding efficiency. The existing generative linguistic steganalysis methods fail to deeply mine text word relation, hence the detection performance is relatively unsatisfactory. In this article, we prove that there is explicit and latent steganography-sensitive text word relation. Based on this, we propose a generative linguistic steganalysis method based on Explicit and Latent text word relation Mining, named ELM. First, we employ a distributed readin module to convert words into real number vectors. Then, MRA (Mining Relation by Attentions) is proposed to mine the explicit and latent text word relation. Finally, global adaptive classification module is presented to exploit the mined relation feature to predict whether secret information is embedded in the current text segment. Experimental results demonstrate that the detection performance of ELM is better than the existing generative linguistic steganalysis methods.
Förderung
- Important Science and Technology Project of Hainan Province
- Frontier Exploration Project Independently Deployed by Institute of Acoustics
- Chinese Academy of Sciences
Zitieren
APA
Li, S., Wang, J., & Liu, P. (2023). Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning. IEEE Transactions on Dependable and Secure Computing, 20(2), 1476-1487. https://doi.org/10.1109/tdsc.2022.3156972
Vancouver
Li S, Wang J, Liu P. Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning. IEEE Transactions on Dependable and Secure Computing. 2023;20(2):1476-1487. doi:10.1109/tdsc.2022.3156972
BibTeX
@article{Li2023,
author = {Li, Songbin and Wang, Jingang and Liu, Peng},
title = {Detection of Generative Linguistic Steganography Based on Explicit and Latent Text Word Relation Mining Using Deep Learning},
journal = {IEEE Transactions on Dependable and Secure Computing},
year = {2023},
volume = {20},
number = {2},
pages = {1476--1487},
doi = {10.1109/tdsc.2022.3156972}
}
EUVIMED