Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems

Abstract

Increasingly autonomous agentic AI systems pose novel multi-agent risks, such as secret collusion via covert communication channels. The natural defence to these collusion attempts is to monitor plain-text communication, but the efficacy of monitors has been called into doubt by increasingly sophisticated model steganography; indeed, some theoretical schemes have been proposed that are information-theoretically or computationally indistinguishable from good-faith plain-text communication. In thi

Categories

Framework mappings

Suggested from the entry's categories.

@misc{rippin2026tool,
  title = {{Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems}},
  author = {Jimmy Laurence Rippin and Simon C. Marshall and David Demitri Africa and Christian Schroeder de Witt},
  year = {2026},
  month = jun,
  eprint = {2606.28425},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.28425}
}