Zero-shot Generative Linguistic Steganography
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909138409226240 |
|---|---|
| author | Lin, Ke Luo, Yiyang Zhang, Zijian Luo, Ping |
| author_facet | Lin, Ke Luo, Yiyang Zhang, Zijian Luo, Ping |
| contents | Generative linguistic steganography attempts to hide secret messages into covertext. Previous studies have generally focused on the statistical differences between the covertext and stegotext, however, ill-formed stegotext can readily be identified by humans. In this paper, we propose a novel zero-shot approach based on in-context learning for linguistic steganography to achieve better perceptual and statistical imperceptibility. We also design several new metrics and reproducible language evaluations to measure the imperceptibility of the stegotext. Our experimental results indicate that our method produces $1.926\times$ more innocent and intelligible stegotext than any other method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_10856 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Zero-shot Generative Linguistic Steganography Lin, Ke Luo, Yiyang Zhang, Zijian Luo, Ping Computation and Language Cryptography and Security Generative linguistic steganography attempts to hide secret messages into covertext. Previous studies have generally focused on the statistical differences between the covertext and stegotext, however, ill-formed stegotext can readily be identified by humans. In this paper, we propose a novel zero-shot approach based on in-context learning for linguistic steganography to achieve better perceptual and statistical imperceptibility. We also design several new metrics and reproducible language evaluations to measure the imperceptibility of the stegotext. Our experimental results indicate that our method produces $1.926\times$ more innocent and intelligible stegotext than any other method. |
| title | Zero-shot Generative Linguistic Steganography |
| topic | Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2403.10856 |