# State-of-the-art Advances of Deep-learning Linguistic Steganalysis Research

arXiv: https://arxiv.org/abs/2409.01780 · HTML: https://mlsanity.com/paper/2409.01780/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 37 references that are in the map.
- First posted on arXiv 3 Sep 2024.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [TS-RNN: Text Steganalysis Based on Recurrent Neural Networks](https://mlsanity.com/paper/1905.13087/) (2019)
- [Exploiting Language Model for Efficient Linguistic Steganalysis](https://mlsanity.com/paper/2107.12168/) (2021)
- [UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysis](https://mlsanity.com/paper/2311.01775/) (2023)
- [Text Steganalysis with Attentional LSTM-CNN](https://mlsanity.com/paper/1912.12871/) (2019)

## Built on by (most cited first, 2 of 2)

- [A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring](https://mlsanity.com/paper/2602.23163/) (2026)
- [Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models](https://mlsanity.com/paper/2601.22818/) (2026)

## Abstract (arXiv)

With the evolution of generative linguistic steganography techniques, conventional steganalysis falls short in robustly quantifying the alterations induced by steganography, thereby complicating detection. Consequently, the research paradigm has pivoted towards deep-learning-based linguistic steganalysis. This study offers a comprehensive review of existing contributions and evaluates prevailing developmental trajectories. Specifically, we first provided a formalized exposition of the general formulas for linguistic steganalysis, while comparing the differences between this field and the domain of text classification. Subsequently, we classified the existing work into two levels based on vector space mapping and feature extraction models, thereby comparing the research motivations, model advantages, and other details. A comparative analysis of the experiments is conducted to assess the performances. Finally, the challenges faced by this field are discussed, and several directions for future development and key issues that urgently need to be addressed are proposed.