Language Model Steganography

Follow this topic Ask about this topic

Latest papers

24 papers1 paper in the last four weeks, down 80% on the four weeks before. 0.0% of all new papers.

Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
Oct 21, 2026Om Tailor, Yucheng Pan, Solaleh Mohammadi +2Language Model Steganography LLM Security
University of Maryland, College Park
StegoMemory: Agentic Memory Acts as Covert Steganographic Channel
Oct 3, 2026Snehasis Mukhopadhyay, Arun NairAI Agent Security Language Model Steganography
Indian Institute of Information Technology, Kalyani · RYVANE
Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Sep 30, 2026Julian Schulz, Lukas Fülle, Rieke FruengelLLM Security Implicit Reasoning in Language Models
Meridian Cambridge · SAIGE
Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion
Sep 24, 2026Qi Pang, Virginia Smith, Wenting ZhengMulti-Agent LLM Systems Algorithmic Collusion
Carnegie Mellon University
For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances
Sep 16, 2026Alexander Shirnin, Aleksey KudelyaDeception in Language Models LLM Security
Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
Sep 14, 2026Danny Wood, James StringerLLM Security Language Model Steganography
Fuzzy Labs
CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding
Sep 9, 2026Wissam Ghantous, Alexander V. MantzarisLLM Security Language Model Steganography
University of Central Florida Orlando, Florida, USA
A Comprehensive Survey on Linguistic Steganography: Methods, Countermeasures, Evaluation, and Challenges
Aug 29, 2026Ruiyi Yan, Chenhui Chu, Zhongliang Yang +1Language Model Steganography
Graduate School of Informatics, Kyoto University · School of Cyberspace Security, Beijing University of Posts and Telecommunications
HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework
Jul 26, 2026Ruiyi Yan, Zhongliang Yang, Yugo MurawakiLLM Security Language Model Steganography
Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan · School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
Jun 25, 2026Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa +1Multi-Agent LLM Systems Multi-Agent Coordination
Oxford University · Artificial Intelligence Security Institute (AISI)
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
Jun 8, 2026Charles Westphal, Timothy Douglas, Keivan Navaie +2LLM Backdoor Attacks Adversarial Attacks on LLMs
UCL Centre for AI, University College London, UK · ML Alignment Theory Scholars, Berkeley, CA, USA · Department of Computer Science, University College London, UK +4
Steganography Without Modification: Hidden Communication via LLM Seeds
Jun 8, 2026Felix Mächtle, Jonas Sander, Sebastian Berndt +3Language Model Decoding LLM Inference
Institute for IT Security, University of Lübeck, Lübeck, Germany · Technische Hochschule Lübeck, Lübeck, Germany
Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion
May 29, 2026Stine Lyngsø Beltoft, William Brach, Federico Torrielli +5LLM Security LLM Safety
University of Southern Denmark · 2Slovak University of Technology in Bratislava · University of Turin +1
Conceptual Steganography
May 26, 2026Zhejian Zhou, Jonathan MayCoT Reasoning LLM Security
University of Southern California · Information Sciences Institute
Detecting Verbatim LLM Copy-Paste in Homework
May 7, 2026Aizierjiang AiersilanText Watermarking AI-Generated Text Detection
The George Washington University
Text Steganography with Dynamic Codebook and Multimodal Large Language Model
Apr 22, 2026Jianxin Gao, Ruohan Lei, Wanli PengLLM Security Language Model Steganography
China Agricultural University Beijing, China
Anchored Sliding Window: Toward Robust and Imperceptible Linguistic Steganography
Apr 10, 2026Ruiyi Yan, Shiao Meng, Yugo MurawakiLanguage Model Steganography Language Model Robustness
Graduate School of Informatics, Kyoto University · School of Software, Tsinghua University
Efficient Provably Secure Linguistic Steganography via Range Coding
Apr 9, 2026Ruiyi Yan, Yugo MurawakiLanguage Model Steganography
Graduate School of Informatics, Kyoto University
Undetectable Conversations Between AI Agents via Pseudorandom Noise-Resilient Key Exchange
Apr 6, 2026Vinod Vaikuntanathan, Or ZamirLanguage Model Steganography AI Agent Security
MIT · Tel Aviv University
Kolmogorov Complexity Bounds for LLM Steganography and a Perplexity-Based Detection Proxy
Mar 23, 2026Andrii ShportkoKolmogorov Complexity Language Model Steganography
Northwestern University Evanston, IL
Invisible Safety Threat: Malicious Finetuning for LLM via Steganography
Mar 9, 2026Guangnian Wan, Xinyin Ma, Gongfan Fang +1Language Model Steganography LLM Security
National University of Singapore
A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring
Feb 26, 2026Usman Anwar, Julianna Piskorz, David D. Baek +6Language Model Steganography LLM Security
University of Cambridge · Massachusetts Institute of Technology · UK AI Safety Institute +3
NEST: Nascent Encoded Steganographic Thoughts
Feb 15, 2026Artem KarpovLanguage Model Safety Evaluation LLM Auditing
Independent.
$\mathbf{S^2LM}$ : Towards Semantic Steganography via Large Language Models
Nov 7, 2025Huanqi Wu, Huangbiao Xu, Yongliang Xu +3Language Model Steganography
College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China

Oct 21, 2026J/K move · Enter open · S save

Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition

Om Tailor, Yucheng Pan, Solaleh Mohammadi, Xinyan Liu+1

University of Maryland, College Park

Language Model Steganography LLM Security Language Model Safety Evaluation Language Model Decoding

Open paper AskPDF arXiv

In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as text transmitted to a decoder, who attempts to recover it. The success of this private-message transmission is commonly measured through end-to-end (E2E) recovery, which checks whether the decoder correctly reconstructs the private message. However, E2E recovery cannot distinguish encoding failures from decoding failures or reveal how the private message is represented in the encoder's transmitted text. To address these limitations, we introduce a rolewise decomposition framework that separately examines how private messages are represented in encoder transmitted texts, what decoders recover, and what deterministic verification can establish. Across 7,200 encoder responses, we identify 168 verifiable encodings missed by decoders and 706 responses containing private messages reconstructed through word-length or token-initial patterns not explicitly specified in the encoder's instructions. These findings demonstrate that E2E recovery alone may obscure important distinctions between encoding and decoding, motivating their separate evaluation to better understand and mitigate the safety issues caused by LLM steganography.