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 (Cornell University)

DOI: 10.48550/arxiv.2610.30516 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Dalam model bahasa besar (LLM) steganografi, encoder menyembunyikan pesan pribadi dalam tanggapan biasa lainnya, sebagai teks yang dikirim ke decoder, yang mencoba untuk memulihkannya. Kesuksesan transmisi pesan pribadi ini biasanya diukur melalui pemulihan end-to-end (E2E), yang memeriksa apakah decoder benar-benar merekonstruksi pesan pribadi. Namun, E2E recovery tidak dapat membedakan kegagalan enkoding dari kegagalan dekoding atau mengungkapkan bagaimana pesan pribadi diwakili dalam teks yang ditransmisikan oleh encoder. Untuk mengatasi keterbatasan ini, kami memperkenalkan kerangka kerja dekomposisi peran yang secara terpisah memeriksa bagaimana pesan pribadi diwakili dalam teks yang ditransmisikan oleh encoder, apa yang dikembalikan decoder, dan apa verifikasi deterministik yang dapat ditetapkan. Di atas 7,200

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 framework that separately examines how private messages are represented in encoder transmitted texts, what decoders recover, and what deterministic verification can establish. Across 7,200 encoder responses, we identify 168 verifiable encodings missed by decoders and 706 responses containing private messages reconstructed through word-length or token-initial patterns not explicitly specified in the encoder's instructions. These findings demonstrate that E2E recovery alone may obscure important distinctions between encoding and decoding, motivating their separate evaluation to better understand and mitigate the safety issues caused by LLM steganography.

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

Topics: Encoding (memory), Encoder, Decoding methods, Computer science, Verifiable secret sharing, Transmission (telecommunications)

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