Saved in:
Bibliographic Details
Main Authors: Pistillo, Matteo, Stix, Charlotte
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.08792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911201683832832
author Pistillo, Matteo
Stix, Charlotte
author_facet Pistillo, Matteo
Stix, Charlotte
contents This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus concerns the open scientific problem of misalignment and its implications on AI model behavior. Specifically, misalignment and scheming capabilities can be a red flag indicating AI model insufficient reliability and governability. To address the national security threats arising from misalignment, we recommend that DoW and the IC strategically leverage existing testing and evaluation pipelines and their OT authority to future proof the principles of AI model reliability and AI model governability through a suite of scheming and control evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_08792
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assurance of Frontier AI Built for National Security
Pistillo, Matteo
Stix, Charlotte
Computers and Society
This memorandum presents four recommendations aimed at strengthening the principles of AI model reliability and AI model governability, as DoW, ODNI, NIST, and CAISI refine AI assurance frameworks under the AI Action Plan. Our focus concerns the open scientific problem of misalignment and its implications on AI model behavior. Specifically, misalignment and scheming capabilities can be a red flag indicating AI model insufficient reliability and governability. To address the national security threats arising from misalignment, we recommend that DoW and the IC strategically leverage existing testing and evaluation pipelines and their OT authority to future proof the principles of AI model reliability and AI model governability through a suite of scheming and control evaluations.
title Assurance of Frontier AI Built for National Security
topic Computers and Society
url https://arxiv.org/abs/2510.08792