Skip to content
AI Sec Watch
LowResearchPeer-reviewedLLM-specific

Prompt-Only LLM Steganography Using a Disentangled Semantic–Stylistic Latent Space and Markov Shaping

Source
IEEE Xplore (Security & AI Journals)(opens in a new tab)
Published
Record updated
View JSON

Summary

Researchers present a prompt-only steganography method for closed LLM APIs that replaces hand-crafted linguistic toggles with a learned, disentangled semantic-stylistic latent space. A beta-VAE maps sentence embeddings to interpretable axes, and prompt directives guide each axis to a binary state, while a reverse arithmetic coding distribution matcher aligns the payload with first-order Markov transition statistics. Across four LLMs and five domains, the method reports about 91% CRC-verified recovery and up to 0.19 bits/token, with moderate, model-dependent detectability (zero-shot AUC 0.54-0.71; adaptive RoBERTa AUC 0.81).

Related items