# Linguistic Steganalysis via LLMs: Two Modes for Efficient Detection of Strongly Concealed Stego

arXiv: https://arxiv.org/abs/2406.04218 · HTML: https://mlsanity.com/paper/2406.04218/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 33 references that are in the map.
- First posted on arXiv 6 Jun 2024.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [TS-RNN: Text Steganalysis Based on Recurrent Neural Networks](https://mlsanity.com/paper/1905.13087/) (2019)
- [Towards Next-Generation Steganalysis: LLMs Unleash the Power of Detecting Steganography](https://mlsanity.com/paper/2405.09090/) (2024)
- [UP4LS: User Profile Constructed by Multiple Attributes for Enhancing Linguistic Steganalysis](https://mlsanity.com/paper/2311.01775/) (2023)
- [Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel](https://mlsanity.com/paper/2401.15656/) (2024)

## Built on by (most cited first, 1 of 1)

- [SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification](https://mlsanity.com/paper/2610.15725/) (2026)

## Abstract (arXiv)

To detect stego (steganographic text) in complex scenarios, linguistic steganalysis (LS) with various motivations has been proposed and achieved excellent performance. However, with the development of generative steganography, some stegos have strong concealment, especially after the emergence of LLMs-based steganography, the existing LS has low detection or cannot detect them. We designed a novel LS with two modes called LSGC. In the generation mode, we created an LS-task "description" and used the generation ability of LLM to explain whether texts to be detected are stegos. On this basis, we rethought the principle of LS and LLMs, and proposed the classification mode. In this mode, LSGC deleted the LS-task "description" and used the "causalLM" LLMs to extract steganographic features. The LS features can be extracted by only one pass of the model, and a linear layer with initialization weights is added to obtain the classification probability. Experiments on strongly concealed stegos show that LSGC significantly improves detection and reaches SOTA performance. Additionally, LSGC in classification mode greatly reduces training time while maintaining high performance.