# REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis

arXiv: https://arxiv.org/abs/2605.28298 · HTML: https://mlsanity.com/paper/2605.28298/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 27 May 2026.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Neural Linguistic Steganography](https://mlsanity.com/paper/1909.01496/) (2019)
- [Generating Steganographic Text with LSTMs](https://mlsanity.com/paper/1705.10742/) (2017)
- [Perfectly Secure Steganography Using Minimum Entropy Coupling](https://mlsanity.com/paper/2210.14889/) (2022)
- [Provably Secure Generative Linguistic Steganography](https://mlsanity.com/paper/2106.02011/) (2021)
- [TS-RNN: Text Steganalysis Based on Recurrent Neural Networks](https://mlsanity.com/paper/1905.13087/) (2019)
- [Automatically Generate Steganographic Text Based on Markov Model and Huffman Coding](https://mlsanity.com/paper/1811.04720/) (2018)
- [Pseudo-label Based Domain Adaptation for Zero-Shot Text Steganalysis](https://mlsanity.com/paper/2406.18565/) (2024)

## Abstract (arXiv)

In real-world scenarios of linguistic steganalysis, tested texts usually come from unseen domains with different vocabularies, topics, writing styles, and steganographic generation patterns, which can significantly degrade the detection performance. Although existing cross-domain steganalysis methods can effectively alleviate this problem through distribution alignment, domain-invariant feature learning, etc., the detection performance is not satisfactory. In this paper, we propose a post-training representation editing method for cross-domain linguistic steganalysis. Specifically, the detector is first trained on source-domain data, and then the feature extractor and classifier are kept frozen, and the intermediate representations are deterministically edited before classification. For domain adaptation, we construct a domain-offset vector from marginal source and target representations. For domain generalization, we derive a source-domain cover-to-stego direction to guide sample-specific editing. Experimental results show that compared with the advanced methods, the proposed method can achieve high cross-domain detection performance, especially in terms of F1-score, while requiring no architecture modification or parameter updates after source-domain training.