Newest papers

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

Om Tailor, Yucheng Pan, Solaleh Mohammadi, Xinyan Liu, Kaiqing Zhang · 2026 · arXiv

DOI: 10.48550/arXiv.2610.30516 · open-access PDF

Spanish

En la steganografía del modelo de lenguaje grande (LLM), un codificador oculta un mensaje privado en una respuesta ordinaria, como texto transmitido a un decodificador, que intenta recuperarlo. El éxito de esta transmisión de mensajes privados se mide comúnmente a través de la recuperación end-to-end (E2E), que verifica si el decodificador reconstruye correctamente el mensaje privado. Sin embargo, la recuperación de E2E no puede distinguir los fallos de codificación de los fallos de decodificación o revelar cómo el mensaje privado está representado en el texto transmitido por el codificador.

Machine translation (Meta M2M100); the English original follows.

Abstract

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 framewo

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30516, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange