Steganography

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 32

All topics

Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard
Sep 30, 2026Julian Schulz, Lukas Fülle, Rieke FruengelSteganography Chain-of-Thought Reasoning
Meridian Cambridge · SAIGE
Codetta: High-Capacity, Keyless, and Undetectable Multi-Agent Collusion
Sep 24, 2026Qi Pang, Virginia Smith, Wenting ZhengSteganography Collusion
Carnegie Mellon University
Permutation-Based Stegomalware in Large Language Models: Threats and Countermeasures
Sep 14, 2026Danny Wood, James StringerAttacker Large Language Model Steganography
Fuzzy Labs
CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding
Sep 12, 2026Wissam Ghantous, Alexander V. MantzarisSteganography Passage Encoding
University of Central Florida Orlando, Florida, USA
A Content-Aware Pure Permutation with Intrinsic Avalanche Effect: Breaking the Diffusion-Permutation Dichotomy
Aug 10, 2026Zahra Ghoraeian, Mohammad-Reza Sadeghi, Samaneh MashhadiPermutation Steganography
Department of Mathematics and Computer Science, Amirkabir University of Technology (Tehran Polytechnic), Tehran, Iran · School of Mathematics and Computer Science, Iran University of Science and Technology, Narmak, Tehran, 1684613114, Iran
From Noise to Meaning: Meaningful Secret Sharing with Tamper Detection for Facial Recognition
Aug 9, 2026Ajnas Muhammed, Iurii Medvedev, Nuno GonçalvesFace Recognition Model Biometrics
Institute of Systems and Robotics, University of Coimbra, Coimbra, Portugal
Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach
Aug 3, 2026Mohamed Chahine GhanemCollusion Steganography
Keele University, Newcastle-Under-Lyme, U.K.
HiTMS: A High-Throughput Multi-Stream Linguistic Steganography Framework
Jul 26, 2026Ruiyi Yan, Zhongliang Yang, Yugo MurawakiSteganography Large Language Model Watermarks
Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan · School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning
Jul 2, 2026Yueming Huang, Wenhan Yao, Fen Xiao +2Clean Label Backdoor Attack Speaker
Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China
No Prompt, No Leaks: A Robust Generative Steganography Framework via Prompt-Free Diffusion
Jun 30, 2026Jingwen Cai, Fen Xiao, Shuhua Deng +1Steganography Latent Diffusion Model
MOE Key Laboratory of Intelligent Computing and Information Processing, Xiangtan University, Xiangtan 411105, China · College of Information Science and Engineering, Hunan Normal University, Changsha 410006, China
IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
Jun 29, 2026Fanye Kong, Hongyu Xia, Yu Zheng +33D Gaussian Steganography
Department of Automation, Tsinghua University, Beijing 100084, China
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
Jun 25, 2026Jimmy Laurence Rippin, Simon C. Marshall, David Demitri Africa +1Steganography Collusion
Oxford University · Artificial Intelligence Security Institute (AISI)
PENet+: A Lightweight Residual Transformer Framework for Efficient Image Steganalysis
Jun 9, 2026Jincheol AN, Dongsu Kim, Haneol Jang +1Steganography Transformer Residual Streams
Department of Artificial Intelligence, Chung-Ang University, Seoul, Korea · Hanbat National University, Department of Computer Engineering, 125, Dongseo-daero, Yuseong-gu, Daejeon, 34158, Korea · 3SNUAILAB, Seoul, Korea
Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs
Jun 8, 2026Charles Westphal, Timothy Douglas, Keivan Navaie +2Steganography Attacker Large Language Model
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 +3Steganography Large Language Model Watermarks
Institute for IT Security, University of Lübeck, Lübeck, Germany · Technische Hochschule Lübeck, Lübeck, Germany
Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection
Jun 7, 2026Mudit Sinha, Sanika ChavanAttacker Large Language Model Steganography
1Lineaje Inc. · 2Arizona State University.
FADRW: A Feature-Aware Modulated and Dynamically Reweighted Loss for Few-Shot Linguistic Steganalysis
Jun 3, 2026Shuo Liu, Xianghong Lin, Yukun Wei +1Steganography Loss Function
International School, Beijing University of Posts and Telecommunications, Beijing 100876, China · School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
REED: Post-Training Representation Editing for Cross-Domain Linguistic Steganalysis
May 27, 2026Ruohan Lei, Jianxin Gao, Wanli Peng +1Steganography Cross-Lingual Transfer
China Agricultural University, Beijing, China · Jiangsu Normal University, Xuzhou, China
On the Origin of Synthetic Information by Means of Steganographic Inheritance
May 26, 2026Ching-Chun Chang, Isao EchizenSteganography Cybersecurity
C.-C. Chang and I. Echizen are with the Information and Society Research Division, National Institute of Informatics, Tokyo, Japan.
Conceptual Steganography
May 26, 2026Zhejian Zhou, Jonathan MaySteganography LLM Reasoning Strategies
University of Southern California · Information Sciences Institute
4D-GSW: Kinematic-Aware Spatio-Temporal Consistent Watermarking for 4D Gaussian Splatting
May 21, 2026Sifan Zhou, Hang Zhang, Yuhang Wang +14D Reconstruction Watermarks
Southeast University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) · University of Chinese Academy of Sciences
DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
May 19, 2026Pengcheng Zhou, Pianran Guo, Shuhua Chen +3Steganography Sharpness-Aware Minimization
Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117583, Singapore · School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
Tackle CSM in JPEG Steganalysis with Data Adaptation
May 19, 2026Rony Abecidan, Vincent Itier, Jérémie Boulanger +2Steganography
CRIStAL · LABEL4.AI, Univ. Lille, CNRS, Centrale Lille, UMR 9189 CRIStAL · IMT Nord Europe, CRIStAL +4
VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense
May 13, 2026Jascha WangerSteganography Vector Database
ThirdKey / Tarnover, LLC
Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses
May 7, 2026Zhen Sun, Zongmin Zhang, Leyi Sheng +7Steganography Query Image
1Wuhan University · 2The Hong Kong University of Science and Technology (Guangzhou) · 3Sun Yat-sen University
Detecting Verbatim LLM Copy-Paste in Homework
May 7, 2026Aizierjiang AiersilanLarge Language Model Watermarks Machine-Generated Text Detection
The George Washington University
Zero-Shot Interpretable Image Steganalysis for Invertible Image Hiding
May 2, 2026Hao Wang, Yiming Yao, Yaguang Xie +2Steganography Image Classification
Zhejiang Provincial Key Laboratory for Sensitive Data Security Protection and Confidentiality Management, Hangzhou Dianzi University, Hangzhou 310018, China · Arcvideo Technology, Hangzhou 310018, China
Quantum Gatekeeper: Multi-Factor Context-Bound Image Steganography with VQC Based Key Derivation on Quantum Hardware
Apr 29, 2026Sahil Tomar, Sandeep KumarSteganography Post-Quantum Cryptography
Central Research Laboratory, BEL, Ghaziabad, India
Text Steganography with Dynamic Codebook and Multimodal Large Language Model
Apr 22, 2026Jianxin Gao, Ruohan Lei, Wanli PengSteganography Large Language Model Watermarks
China Agricultural University Beijing, China
Splats in Splats++: Robust and Generalizable 3D Gaussian Splatting Steganography
Apr 17, 2026Yijia Guo, Wenkai Huang, Tong Hu +9Steganography 3D Generation
State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, 100871, China · Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China · National Biomedical Imaging Center, College of Future Technology, Peking University, Beijing, 100871, China +2
Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution
Apr 11, 2026Robert DilworthStylometric Anonymization
Department of Computer Science and Engineering, Mississippi State University, Mississippi State, Mississippi, USA
NEST: Nascent Encoded Steganographic Thoughts
Feb 15, 2026Artem KarpovSteganography Chain-of-Thought Reasoning
Independent.

Sep 30, 2026, cs.AIJ/K move · Enter open · S save

Learning Steganography Is Easy, Learning Steganographic Reasoning Is Hard

Julian Schulz, Lukas Fülle, Rieke Fruengel

Meridian Cambridge · SAIGE

Steganography Chain-of-Thought Reasoning Elicitation

Open paper AskPDF arXiv

Chain-of-thought monitoring as an approach for AI oversight and control is threatened by the possibility of steganographic reasoning, where LLMs conceal their reasoning inside innocuous-looking text. Two neighbouring capabilities, steganographic messaging (passing a concealed message) and encoded reasoning (reasoning in an illegible but unconcealed format), have already been shown to emerge under training pressures that occur in real pipelines, such as reinforcement learning against monitors. This suggests that steganographic reasoning too might arise as an unintended side effect of training. Here, we compare how easily models learn steganographic reasoning and these two neighbouring capabilities across three elicitation methods: reinforcement learning, in-context learning, and supervised fine-tuning (SFT). For most tasks, models learn steganographic reasoning only under SFT, while they learn steganographic messaging and encoded reasoning under all three elicitation methods. Even under SFT, steganographic reasoning requires at least twice as much training as messaging, and for several model-task combinations it is not learned at all. However, on a cover task that makes hiding information especially convenient, steganographic reasoning can be successfully learned under all three elicitation methods. Steganographic reasoning is thus much harder than steganographic messaging and encoded reasoning, and learning the latter two does not imply learning the former. Yet it lies within reach: an easy version is learned under every elicitation method, when the cover task is convenient for hiding information.

Momentum

Related topics

Latest papers 32