Metraipolis › archive › dc_bd4e1012dc60

Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach? — arXiv:2608.27443

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.27443
License (as archived): CC0-1.0
Archived: 2026-10-17T15:55:23.842Z
SHA-256 of the archived text: 84e49d1d0cebc0d894267860632c1b88f438575ed7d93e37149416bd15ef2984
Stable URL of this page: https://metraipolis.com/documento/dc_bd4e1012dc60

How to cite

Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach? — arXiv:2608.27443 — arXiv (en), https://arxiv.org/abs/2608.27443 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd4e1012dc60 (Metraipolis archive dc_bd4e1012dc60, sha256 84e49d1d0cebc0d894267860632c1b88f438575ed7d93e37149416bd15ef2984)

BibTeX

@misc{dcbd4e1012dc60,
  title = {Do User-Authored Permission Policies Improve Protection Against AI Agent Overreach? — arXiv:2608.27443},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27443},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd4e1012dc60; sha256 84e49d1d0cebc0d894267860632c1b88f438575ed7d93e37149416bd15ef2984},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27443. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents are poised to become a primary interface to digital products, acting across email, files, payments, and personal data. People without professional software backgrounds need understandable, reusable ways to control actions across services. We examine a mechanism in which a language model maps actions to plain-language consequence categories with user-authored "allow", "ask", or "never" rules. We ask what is gained and lost when decisions are made in advance as reusable rules rather than separately for each action. We analyzed 113 participants without professional software backgrounds across three conditions: per-action human-in-the-loop approval (HITL), automated per-action model review (AUTO), or user-authored consequence policy (POLICY). Participants judged 2 examples in each of 4 consequence categories; POLICY participants then set one rule per category. All supervised an 18-action simulated day, including 7 overreach actions. POLICY blocked less overreach than HITL (-20.1 percentage points, 95% CI [-32.1, -8.1]) and AUTO (-14.5 points, 95% CI [-25.8, -3.2]). POLICY lowered runtime prompts from 18.0 to 10.9, but total intervention time was not reliably lower when rule setup was included. Exploratory analysis showed that participants chose "ask" for 114 of 140 POLICY rules, returning most overreach actions to runtime. Of the 148 overreach actions executed in POLICY, 133 followed human approval and 15 ran automatically under "allow" rules. Across all 7 overreach actions, POLICY had the highest approval rate. Counterintuitively, user-authored rules did not by themselves provide stronger protection: many actions outside users' original requests went through after users approved them. These results reveal a gap between preference and commitment: repeatedly choosing "ask" preserves case-by-case choice but prevents a standing policy from settling decisions in advance.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CR).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.27443 — 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 2026-10-17T15:31:38.290Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).