Selected primary research # A reading list for linguistic steganography Methods, guarantees, reliability, and related uses of generated text. Ordered by earliest documented date. The paper pages distinguish manuscript dates, first preprints, and published versions and explain each work’s relationship to Neural Linguistic Steganography. This is a curated starting point, not an exhaustive survey. Search titles, authors, or concepts TopicAll topicsAgent communicationEarly neural approachesExtensions and reliabilityNeural Linguistic SteganographySecurity and distribution matchingWatermarking OrderOldest firstNewest firstTitle A–Z Reset 10 papers · all entries are available without JavaScript Search and sorting need JavaScript. All papers and citation downloads are listed below. 2017 Early neural approaches ## [Generating Steganographic Text with LSTMs](https://steganography.live/reading-list/papers/fang-2017/) Tina Fang, Martin Jaggi, Katerina Argyraki Uses an LSTM language model and vocabulary bins to generate text carrying a secret bitstream. Experiments on tweets and email explore the trade-off between embedding capacity and text quality. First arXiv submission: May 30, 2017 · ACL 2017 Student Research Workshop [Read notes & citations →](https://steganography.live/reading-list/papers/fang-2017/) · [Primary source ↗](https://aclanthology.org/P17-3017/) 2018 Early neural approaches ## [RNN-Stega: Linguistic Steganography Based on Recurrent Neural Networks](https://steganography.live/reading-list/papers/rnn-stega/) Zhong-Liang Yang, Xiao-Qing Guo, Zi-Ming Chen, Yong-Feng Huang, Yu-Jin Zhang Generates cover text with a recurrent language model and dynamically encodes candidate words using fixed-length or Huffman variable-length codes. It evaluates generation efficiency, embedding capacity, text quality, and resistance to the tested steganalysis methods. First online publication (IEEE): September 24, 2018 · IEEE TIFS 2019 (online 2018) [Read notes & citations →](https://steganography.live/reading-list/papers/rnn-stega/) · [Primary source ↗](https://ieeexplore.ieee.org/document/8470163) 2019 Security and distribution matching ## [Towards Near-imperceptible Steganographic Text](https://steganography.live/reading-list/papers/dai-cai-2019/) Falcon Z. Dai, Zheng Cai Analyzes how binning and variable-length encoding alter a language model's output distribution. Its patient-Huffman method skips message embedding at steps where the induced distribution would differ too much from the model. First arXiv submission: July 15, 2019 · ACL 2019 [Read notes & citations →](https://steganography.live/reading-list/papers/dai-cai-2019/) · [Primary source ↗](https://aclanthology.org/P19-1422/) 2019 Neural Linguistic Steganography ## [Neural Linguistic Steganography](https://steganography.live/reading-list/papers/neural-linguistic-steganography/) Zachary M. Ziegler*, Yuntian Deng*, Alexander M. Rush 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. First arXiv submission: September 3, 2019 · EMNLP-IJCNLP 2019 [Read notes & citations →](https://steganography.live/reading-list/papers/neural-linguistic-steganography/) · [Primary source ↗](https://aclanthology.org/D19-1115/) 2020 Extensions and reliability ## [Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding](https://steganography.live/reading-list/papers/saac/) Jiaming Shen, Heng Ji, Jiawei Han Introduces self-adjusting arithmetic coding, choosing the candidate-set size at each generation step to control divergence from the language model. It supplies an imperceptibility analysis and evaluates capacity, divergence, and human judgments across multiple datasets. First arXiv submission: October 1, 2020 · EMNLP 2020 [Read notes & citations →](https://steganography.live/reading-list/papers/saac/) · [Primary source ↗](https://aclanthology.org/2020.emnlp-main.22/) 2022 Security and distribution matching ## [Perfectly Secure Steganography Using Minimum Entropy Coupling](https://steganography.live/reading-list/papers/minimum-entropy-coupling/) Christian Schroeder de Witt*, Samuel Sokota*, J. Zico Kolter, Jakob Foerster, Martin Strohmeier Characterizes perfect steganographic security through couplings and maximal information throughput through minimum entropy couplings under its information-theoretic model. It develops an iterative method and compares it with arithmetic coding, Meteor, and adaptive dynamic grouping on text, audio, and image-model distributions. First arXiv submission: October 24, 2022 · ICLR 2023 [Read notes & citations →](https://steganography.live/reading-list/papers/minimum-entropy-coupling/) · [Primary source ↗](https://openreview.net/forum?id=HQ67mj5rJdR) 2023 Watermarking ## [A Watermark for Large Language Models](https://steganography.live/reading-list/papers/llm-watermark/) John Kirchenbauer*, Jonas Geiping*, Yuxin Wen, Jonathan Katz, Ian Miers, Tom Goldstein Embeds a statistical watermark by softly favoring a pseudorandom set of tokens during generation. It develops a detection test that does not require the language model and analyzes how the token distribution affects detection strength. First arXiv submission: January 24, 2023 · ICML 2023 [Read notes & citations →](https://steganography.live/reading-list/papers/llm-watermark/) · [Primary source ↗](https://proceedings.mlr.press/v202/kirchenbauer23a.html) 2024 Agent communication ## [Secret Collusion among AI Agents: Multi-Agent Deception via Steganography](https://steganography.live/reading-list/papers/secret-collusion/) Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H.S. Torr, Lewis Hammond, Christian Schroeder de Witt Formalizes secret collusion among generative AI agents and develops capability evaluations for covert communication and coordination. It studies individual and multi-agent settings alongside the assumptions and limitations of monitoring and other mitigations. First arXiv submission: February 12, 2024 · NeurIPS 2024 [Read notes & citations →](https://steganography.live/reading-list/papers/secret-collusion/) · [Primary source ↗](https://proceedings.neurips.cc/paper_files/paper/2024/hash/861f7dad098aec1c3560fb7add468d41-Abstract-Conference.html) 2024 Extensions and reliability ## [Provably Secure Disambiguating Neural Linguistic Steganography](https://steganography.live/reading-list/papers/syncpool/) Yuang Qi, Kejiang Chen, Kai Zeng, Weiming Zhang, Nenghai Yu Introduces SyncPool to resolve subword segmentation ambiguity while preserving the model's token distribution. It groups prefix-related tokens and uses synchronized pseudorandom sampling so a receiver can recover token choices from detokenized text. First arXiv submission: March 26, 2024 · IEEE TDSC 2025 (preprint 2024) [Read notes & citations →](https://steganography.live/reading-list/papers/syncpool/) · [Primary source ↗](https://ieeexplore.ieee.org/document/10804596) 2025 Extensions and reliability ## [Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models](https://steganography.live/reading-list/papers/tokenization/) Ruiyi Yan, Yugo Murawaki Studies tokenization inconsistencies between generated token sequences and the text a receiver retokenizes. It proposes stepwise verification for steganography and post-hoc rollback for watermark detection, evaluating how these changes affect reliability, text quality, and detection. First arXiv submission: August 28, 2025 · EMNLP 2025 [Read notes & citations →](https://steganography.live/reading-list/papers/tokenization/) · [Primary source ↗](https://aclanthology.org/2025.emnlp-main.361/) No papers match those filters. Try a broader term or reset the filters.