Abstract
We show that the imperceptibility of several existing linguistic steganographic systems (Fang et al., 2017; Yang et al., 2018) relies on implicit assumptions on statistical behaviors of fluent text. We formally analyze them and empirically evaluate these assumptions. Furthermore, based on these observations, we propose an encoding algorithm called patient-Huffman with improved near-imperceptible guarantees.- Anthology ID:
- P19-1422
- Volume:
- Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Anna Korhonen, David Traum, Lluís Màrquez
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4303–4308
- Language:
- URL:
- https://aclanthology.org/P19-1422
- DOI:
- 10.18653/v1/P19-1422
- Cite (ACL):
- Falcon Dai and Zheng Cai. 2019. Towards Near-imperceptible Steganographic Text. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4303–4308, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Towards Near-imperceptible Steganographic Text (Dai & Cai, ACL 2019)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/P19-1422.pdf
- Code
- falcondai/lm-steganography