mlsanityData to 14 Oct 2026

Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography

arXiv 2604.09066 ↗First posted 10 Apr 2026cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

Linguistic steganography based on language models typically assumes that steganographic texts are transmitted without alteration, making them fragile to even minor modifications. While previous work mitigates this fragility by limiting the context window, it significantly compromises text quality. In this paper, we propose the anchored sliding window (ASW) framework to improve imperceptibility and robustness. In addition to the latest tokens, the prompt and a bridge context are anchored within the context window, encouraging the model to compensate for the excluded tokens. We formulate the optimization of the bridge context as a variant of prompt distillation, which we further extend using self-distillation strategies. Experiments show that our ASW significantly and consistently outperforms the baseline method in text quality, imperceptibility, and robustness across diverse settings. The code is available at github.com/ryehr/ASW_steganography.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 20 of its 49 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

20 of 49 references.

References · 20

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,307
  5. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  6. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,186
  7. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 868
  8. 2016Sequence-Level Knowledge Distillationcited by 801
  9. 2024Non-Determinism of "Deterministic" LLM Settingscited by 92
  10. 2024Coercing LLMs to do and reveal (almost) anythingcited by 89
  11. 2019Neural Linguistic Steganographycited by 78
  12. 2017Generating Steganographic Text with LSTMscited by 44
8 more
  1. 2022Perfectly Secure Steganography Using Minimum Entropy Couplingcited by 44
  2. 2021Provably Secure Generative Linguistic Steganographycited by 34
  3. 2019Towards Near-imperceptible Steganographic Textcited by 32
  4. 2020LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuningcited by 25
  5. 2020Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Codingcited by 17
  6. 2025SparSamp: Efficient Provably Secure Steganography Based on Sparse Samplingcited by 14
  7. 2022Addressing Segmentation Ambiguity in Neural Linguistic Steganographycited by 7
  8. 2024Provably Robust and Secure Steganography in Asymmetric Resource Scenariocited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Frameworkcited by 1
  2. 2026A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challengescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
  2. 2026Synchronized Logit Steering: Real-world Steganography
  3. 2025Hiding in Plain Sight: A Steganographic Approach to Stealthy LLM Jailbreaks
  4. 2025Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models
  5. 2026Conceptual Steganography
  6. 2024Dynamically Allocated Interval-Based Generative Linguistic Steganography with Roulette Wheel
  7. 2026Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models
  8. 2026Feedback Coding Enables Inference-Time Covert Agentic Communication