The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era by identifying five specific paradigm shifts in the LLM era.
Abstract
Linguistic steganography hides secret messages in natural language text. Large language models (LLMs) have reshaped the field, but a systematic account of how these scattered advances collectively reshape the field in this new era is still missing. We provide one along four axes: 148 steganographic methods, 60 linguistic steganalysis countermeasures, 23 evaluation metrics, and 9 open challenges, each with taxonomies, reviews, and adoption analyses. Cutting across these axes, we identify five specific paradigm shifts in the LLM era: (1) from covertext modification to prompt-only generation, (2) from heuristic to provable security, (3) from white-box symmetric LMs to black-box or asymmetric access, (4) from security-centric designs to joint optimization, and (5) from text-quality concerns to engineering issues. The survey aims to serve as both a reference and a roadmap for practical and responsible linguistic steganography in the LLM era.
This paper demonstrates the full potential of behavior-preserving symmetries as a defense against stegomalware, as well as the risks these symmetries pose when exploited by attackers, and quantifies the loss in model performance associated with applying these methods.
This verifiability-focused review analyzes an enumerated, non-exhaustive corpus of 45 content- and context-based detection studies in which each reported headline metric is traced to its primary source and confirmed against it wherever the source is accessible, and derives a dependency-ordered research agenda and trans...
Long Dinh Tuan, L. N. An, Duong Dinh Thai· Journal of Computing Theorie...· 0 citations
A robust coverless steganographic framework that operates in the sentence embedding space rather than the token space is proposed that achieves substantial improvements in robustness, while maintaining effective embedding capacity and exhibiting strong resistance to statistical analysis.
Li-Zhi Xiong, Yu-Ping Lu, Jun Li et al.· 0 citations
Large language models (LLMs) increasingly power autonomous coding agents such as Codex and Claude Code, yet their training corpora may contain confidential credentials exposed in public repositories or collected from private development artifacts, creating risks of memorization and subsequent leakage. Existing extracti...
Shi-Qian Zhao, Si-Wei Jiang, Xin-Feng Li et al.· 0 citations
Results show that the copy–paste attack degrades watermark detectability when using very sparingly and only short sentences are used, while deletion becomes effective only at extreme levels on short texts, and underscore the need for future watermark designs to prioritise resilience to semantic and cross-lingual transf...
Jakob Elias Albrecht, A. Jakoby, Benno Maria et al.· 0 citations
(k)-SwordStamp is designed: semantic watermarks with order-robust detection over sub-sentence units, reducing sensitivity to attacker-chosen structure at a small quality cost.
Abdulrahman Diaa, Jonathan Petit, Florian Kerschbaum· 2 citations
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
