Paper Detail

Feedback Coding Enables Inference-Time Covert Agentic Communication

Sidong Guo, Sajani Vithana, Atefeh Gilani, Lalitha Sankar, Oliver Kosut, Flavio P. Calmon

arxiv Score 11.3

Published 2026-09-21 · First seen 2026-09-22

General AI

Abstract

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{B}urnashev \textbf{A}daptive Posterior \textbf{M}atching (BAM), a feedback-coding scheme that combines posterior matching with a decode-and-confirm phase. The design is inspired by classical information-theoretic feedback-coding principles, while its security is established through a cryptographic reduction proof. Across three open-weight language models, we demonstrate that BAM attains 0-0.1\% empirical message error on an 8-bit payload in around 50 tokens, across 1000 trials, versus 10-17\% for the strongest black-box baseline at comparable length. Building on the proposed steganography algorithm, we demonstrate the feasibility of an end-to-end communication protocol that achieves high communication rates across multiple conversational settings.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{guo2026feedback,
  title = {Feedback Coding Enables Inference-Time Covert Agentic Communication},
  author = {Sidong Guo and Sajani Vithana and Atefeh Gilani and Lalitha Sankar and Oliver Kosut and Flavio P. Calmon},
  year = {2026},
  abstract = {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 c},
  url = {https://arxiv.org/abs/2609.24994},
  keywords = {cs.IT, cs.CR},
  eprint = {2609.24994},
  archiveprefix = {arXiv},
}

Metadata

{}