{"data":{"id":"268f4355-4604-401e-be9c-091b728789bb","title":"Prompt-Only LLM Steganography Using a Disentangled Semantic–Stylistic Latent Space and Markov Shaping","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).","solution":"N/A -- no mitigation discussed in source.","labels":["research","security"],"sourceUrl":"http://ieeexplore.ieee.org/document/11741293","publishedAt":"2026-10-19T05:06:46.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"low","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["OpenAI","Anthropic"],"affectedVendorsRaw":["GPT-4.1 nano","GPT-5 nano","Claude 4.5 Haiku","Claude 4.5 Sonnet"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-19T05:06:46.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["confidentiality"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":null}}