Om Tailor, Yucheng Pan, Solaleh Mohammadi, Xinyan Liu, Kaiqing Zhang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30516 · open-access PDF
대형 언어 모델 (LLM) 스테가노그래피에서, 인코더는 대개 평범한 응답으로, 디코더로 전송되는 텍스트로 개인 메시지를 숨깁니다.이 개인 메시지 전송의 성공은 일반적으로 엔드-테인드(E2E) 복구를 통해 측정되며, 이는 디코더가 개인 메시지를 올바르게 재구성하는지 확인합니다.그러나, E2E 복구는 인코딩 실패와 디코딩 실패를 구별하거나 개인 메시지가 인코더의 전송된 텍스트에서 어떻게 표현되는지를 밝힐 수 없습니다.이 제한을 해결하기 위해, 우리는 역할별 분해 프레임워크를 도입합니다.
Machine translation (Meta M2M100); the English original follows.
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
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange