Metraipolis › archive › dc_3c6db47669fe

When AI Finds Hidden Messages, Does It Report? — arXiv:2610.10620

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10620
License (as archived)
CC0-1.0
Archived
2026-10-09T05:53:33.862Z
SHA-256 of the archived text
e92b7c6512616aa040972056db2bd717e69c8b0e7b4fcf533a3eab36880cf985
Stable URL of this page
https://metraipolis.com/documento/dc_3c6db47669fe

How to cite

When AI Finds Hidden Messages, Does It Report? — arXiv:2610.10620 — arXiv (en), https://arxiv.org/abs/2610.10620 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3c6db47669fe (Metraipolis archive dc_3c6db47669fe, sha256 e92b7c6512616aa040972056db2bd717e69c8b0e7b4fcf533a3eab36880cf985)
BibTeX
@misc{dc3c6db47669fe,
  title = {When AI Finds Hidden Messages, Does It Report? — arXiv:2610.10620},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10620},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3c6db47669fe; sha256 e92b7c6512616aa040972056db2bd717e69c8b0e7b4fcf533a3eab36880cf985},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10620. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When an assistant encounters a message for another AI, does it tell its user? Four fixed model-provider deployments perform simulated source tasks in 1,280 ordinary-note and 128 enhanced-note sessions. Harmless and harmful messages have matched plaintext and ROT13 versions, with no-message controls. Observers receive no decoder or decoded meaning; a requested reference code incentivizes inspection. Asking for reports increases rule-detected notifications identifying another AI as recipient by 53.1 percentage points for harmless ROT13 messages and 54.7 for harmful ones. This is a joint inspection, recognition, and notification effect; missing-response bounds are 38.3--77.3 and 36.7--78.1 points. Model-based trace checks identify eleven ordinary plaintext cases where agents interpret the message but do not notify their user. Seven encoded omissions are verified with enhanced notes; ordinary encoded omissions remain unverified. Seven simulated filename disclosures coexist with accurate review-status answers, and two answers use a planted false count. Interpretation, notification, and authorized task performance are distinct outcomes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.10620 — 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 2026-10-09T05:47:01.212Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).