Metraipolis › archive › dc_ecebce00f0f7

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach — arXiv:2608.02698

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02698
License (as archived)
CC0-1.0
Archived
2026-10-31T12:17:41.806Z
SHA-256 of the archived text
78460dabba50aa7421a5cc67b821bd7b5df30bda8fa09dbd28df38cb1e5af713
Stable URL of this page
https://metraipolis.com/documento/dc_ecebce00f0f7

How to cite

Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach — arXiv:2608.02698 — arXiv (en), https://arxiv.org/abs/2608.02698 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecebce00f0f7 (Metraipolis archive dc_ecebce00f0f7, sha256 78460dabba50aa7421a5cc67b821bd7b5df30bda8fa09dbd28df38cb1e5af713)
BibTeX
@misc{dcecebce00f0f7,
  title = {Steganalysis of Adaptive Covert Collusion in Tool-Using Agent Populations: A Black-Box, Cross-Principal Approach — arXiv:2608.02698},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02698},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecebce00f0f7; sha256 78460dabba50aa7421a5cc67b821bd7b5df30bda8fa09dbd28df38cb1e5af713},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02698. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-using agents built on large language models (LLMs) are increasingly deployed not by a single operator but by many, side by side on shared infrastructure. This creates a population-level risk that single-agent safeguards miss: a handful of agents can quietly coordinate, rigging a market, boosting one another in a review process, or timing a joint data grab, while each one looks perfectly well-behaved. The difficulty is that the organisations running these agents cannot see inside one another's models, so any realistic detector must work from behaviour alone: black-box, trace-only, and often with only partial visibility. We treat covert coordination as an information-hiding problem and build a black-box steganalysis detector that combines cross-run mutual-information estimation, permutation tests, distributional-shift statistics, and timing and tool-call side channels, all calibrated to a fixed false-positive budget. Our central move is to stop testing against a single fixed code: we pit the detector against an adversary that continually rewrites its encoding to slip past whatever the detector has learned, and we run this red-versus-blue contest in tool-using, memory-carrying environments rather than toy games. Capacity theory then tells us what to expect, a detection-capacity frontier, a covert bit-rate below which black-box detection is provably no better than chance. We set out an experiment to map this frontier, report clearly labelled placeholder results pending measurement, and flag a practical evasion, spreading a payload across sessions, that current methods largely miss.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02698 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:52.939Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).