Abstract
With advances in neural language models, the focus of linguistic steganography has shifted from edit-based approaches to generation-based ones. While the latter’s payload capacity is impressive, generating genuine-looking texts remains challenging. In this paper, we revisit edit-based linguistic steganography, with the idea that a masked language model offers an off-the-shelf solution. The proposed method eliminates painstaking rule construction and has a high payload capacity for an edit-based model. It is also shown to be more secure against automatic detection than a generation-based method while offering better control of the security/payload capacity trade-off.- Anthology ID:
- 2021.naacl-main.433
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5486–5492
- Language:
- URL:
- https://aclanthology.org/2021.naacl-main.433
- DOI:
- 10.18653/v1/2021.naacl-main.433
- Cite (ACL):
- Honai Ueoka, Yugo Murawaki, and Sadao Kurohashi. 2021. Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5486–5492, Online. Association for Computational Linguistics.
- Cite (Informal):
- Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model (Ueoka et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/jeptaln-2024-ingestion/2021.naacl-main.433.pdf
- Code
- ku-nlp/steganography-with-masked-lm