Metraipolis › archive › dc_3e4986efe342

Cross-Interface Authorization for AI Computer-Use Agents — arXiv:2610.41397

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41397
License (as archived): CC0-1.0
Archived: 2026-11-03T05:23:52.504Z
SHA-256 of the archived text: 5295ed01cf6caa4d79544c67c7ab5bc2c8545007a3474eecf5fba82b794ff30d
Stable URL of this page: https://metraipolis.com/documento/dc_3e4986efe342

How to cite

Cross-Interface Authorization for AI Computer-Use Agents — arXiv:2610.41397 — arXiv (en), https://arxiv.org/abs/2610.41397 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3e4986efe342 (Metraipolis archive dc_3e4986efe342, sha256 5295ed01cf6caa4d79544c67c7ab5bc2c8545007a3474eecf5fba82b794ff30d)

BibTeX

@misc{dc3e4986efe342,
  title = {Cross-Interface Authorization for AI Computer-Use Agents — arXiv:2610.41397},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41397},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3e4986efe342; sha256 5295ed01cf6caa4d79544c67c7ab5bc2c8545007a3474eecf5fba82b794ff30d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41397. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computer-use agents act through graphical interfaces, command lines, APIs, scripts, and Model Context Protocol servers. A policy decision can be interface-invariant while its executable authorization is not: another route can bypass mediation, alter a security-relevant default, or commit after the authorized state has changed. We present a profile-bounded protocol for a fixed, versioned computer-use deployment. It enumerates effect-bearing routes and durable sinks, checks a route-to-sink enforcement cut, normalizes each concrete request to a canonical effect, issues a route-bound prepare ticket, and verifies the route, effect, grant, trace, profile, inventory, and authoritative state again at commit. A committed result requires an agreeing sink receipt. Under explicit assumptions, we prove profile-bounded refinement, matched-effect decision invariance, resistance to alternate-route laundering and declared cross-surface recomposition, commit-time state safety, and receipt-grounded outcomes. The reference profile registers 12 effect families, five interfaces, and 60 routes. Two structurally distinct runtime mappings produce 3,464 traces over 1,732 scenarios each: 960 commits, 2,312 denials, and 192 commits after re-preparation. An independent checker accepts every retained trace and pair and rejects 26/26 semantic regressions; coverage and normalizer suites reject 24/24 and 720/720 mutants; and 168/168 commit probes match their declared outcomes. A frozen-source audit passes 52 checks over 12 files from two independent hybrid runtimes and one public authorization substrate. Source-shaped adapter refinements commit 48/48 instrumented calls and reject 15/15 unbound cases. The resulting guarantees bind the declared profile and its effect semantics.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.41397 — 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 2026-11-03T05:18:52.120Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).