Neural text steganography methods
Compare vocabulary bins, Huffman coding, patient-Huffman, arithmetic coding, self-adjusting arithmetic coding, and minimum entropy coupling, with primary papers and implementation context.
Papers · explanations · citations
Neural Linguistic
Steganography
Hidden messages. Generated language.
Neural text steganography, also called neural linguistic steganography, encodes hidden messages in generated language. Explore vocabulary bins, Huffman coding, arithmetic coding, and distribution-preserving methods alongside their security assumptions and experiments.
Neural text steganography methods
Compare the methods, follow the mechanism, and examine the guarantees and connections.
How does arithmetic coding hide a message in text?
Follow the path from secret bits to language-model token choices, and back again.
Capacity, detectability, and security are different measurements
Read steganography results by asking what is measured, which distribution is protected, and what the observer can do.
From hidden messages to watermarks and agent communication
Shared token-level ideas connect these fields, while their objectives and evidence remain distinct.
The original project
Neural Linguistic
Steganography
First arXiv submission · September 3, 2019
Published · EMNLP-IJCNLP, November 2019
Neural Linguistic Steganography
* Equal contribution.
Combines arithmetic coding with large pretrained language models to encode secret information into generated text while closely matching the model's distribution. GPT-2 experiments evaluate information capacity, statistical divergence, and human judgments of contextual continuations, and demonstrate encoding natural-language messages into unrelated cover text.
The paper develops neural language-model steganography through arithmetic coding, with analysis of the induced distribution and experiments on message capacity and generated text. STEGASURAS is the interactive demonstration accompanying this work.
A short reading path
Distribution and security → Neural Linguistic Steganography → Self-adjusting arithmetic coding → Minimum entropy coupling → Tokenization reliability
Then follow the connection to watermarking and agent communication. A citation, a shared mechanism, and a direct extension are different relationships; each paper note explains the connection supported by its sources.
Browse the full bibliography → · Download citations and reading notes →