Feedback Coding Enables Inference-Time Covert Agentic Communication
[cs.IT] Autorzy: Sidong Guo, Sajani Vithana, Atefeh Gilani i 3 więcej
As large language models (LLMs) are increasingly used to automate digital interactions, users can leverage LLM-generated text as cover for covert communication within seemingly benign conversations. Existing LLM steganography, however, is predominantly white-box, requiring the sender and receiver to share the cover statistics, typically through access to the model weights and prompt. Black-box schemes remove this requirement by allowing the receiver to operate solely on the generated text, but current approaches rely on fixed-length, open-loop watermarking techniques that suffer from high decoding error rates under variable-length token generation. We recast black-box LLM steganography as a sequential communication problem with causal, noiseless feedback: every generated token is observed by both parties and can guide subsequent embedding. Based on this perspective, we introduce \textbf…
- Kategoria arxiv
- cs.IT
- Kategoria
- cs.IT